Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to decision-making and acknowledgment of actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Preposition "to" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    approaching a point or destination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fört
    -0.56
    jws
    -0.54
    ersk
    -0.51
    mingo
    -0.47
     övers
    -0.47
    weit
    -0.45
     sendi
    -0.44
    人民共和国
    -0.43
    casian
    -0.43
     Anspruch
    -0.43
    POSITIVE LOGITS
    yntaxException
    0.82
     betweenstory
    0.78
    RegressionTest
    0.77
     newOwner
    0.74
    principalColumn
    0.73
     rid
    0.72
     '\\;'
    0.72
    SharedDtor
    0.71
     ProtoMessage
    0.70
     <>",
    0.70
    Act Density 0.054%

    No Known Activations