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

    Neuronpedia

    INDEX
    Explanations

    key structural elements and terms associated with organizations and systems

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

    methadone, ACHS, .NET

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    -0.32
    ,
    -0.28
     ál
    -0.28
     draft
    -0.25
    Alu
    -0.25
     battle
    -0.25
    modelBuilder
    -0.25
    ('../../
    -0.24
     Alu
    -0.24
     mejor
    -0.24
    POSITIVE LOGITS
    majánló
    0.82
     vooz
    0.80
    ConstraintMaker
    0.80
    <unused8>
    0.79
    <unused28>
    0.79
    <unused16>
    0.79
    <unused51>
    0.79
    <unused79>
    0.79
    <unused14>
    0.78
    <unused17>
    0.78
    Act Density 0.116%

    No Known Activations