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

    Neuronpedia

    INDEX
    Explanations

    references to locations or inquiries regarding locations

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

    Followed by a question

    np_acts-logits-general · gemini-2.0-flash

    where does

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dlaczego
    -0.60
    them
    -0.57
    }{*}{
    -0.55
     bagaimana
    -0.53
     őket
    -0.52
    ième
    -0.52
    sS
    -0.52
     način
    -0.51
     manières
    -0.51
    Fazit
    -0.50
    POSITIVE LOGITS
    ever
    1.22
     else
    1.10
    upon
    1.08
     they
    1.01
    quiera
    0.97
     we
    0.95
     there
    0.89
    by
    0.89
    ver
    0.88
    VER
    0.79
    Act Density 0.089%

    No Known Activations