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

    Neuronpedia

    INDEX
    Explanations

    present tense forms of the verb "to be" or related verbs indicating states or actions

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

    what's + state/action/prediction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administração
    -0.56
     rowIndex
    -0.50
     Infór
    -0.47
     braços
    -0.47
    outheast
    -0.47
    upported
    -0.47
    Grü
    -0.46
    skir
    -0.46
     PERFECT
    -0.46
    explicit
    -0.46
    POSITIVE LOGITS
     whats
    0.73
    whats
    0.69
    Whats
    0.63
     Whats
    0.61
     neler
    0.44
     what
    0.42
     AssemblyVersion
    0.41
    What
    0.40
    何が
    0.39
    mstyle
    0.39
    Act Density 0.006%

    No Known Activations