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

    Neuronpedia

    INDEX
    Explanations

    mathematical equations and expressions

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

    mathematical equations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     marshmallows
    -0.38
     Berea
    -0.34
    ToAction
    -0.34
    Ju
    -0.33
    Mara
    -0.33
    Leak
    -0.33
    Justin
    -0.32
    Hor
    -0.32
     Conspiracy
    -0.31
    Ber
    -0.30
    POSITIVE LOGITS
    rungsseite
    0.82
    bootstrapcdn
    0.80
    RegressionTest
    0.60
    StructEnd
    0.58
     defaultstate
    0.58
     sumpay
    0.57
     iprot
    0.57
    MessageOf
    0.57
    setVerticalGroup
    0.56
    GOTREF
    0.56
    Act Density 0.128%

    No Known Activations