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

    Neuronpedia

    INDEX
    Explanations

    schema definition in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     puisqu
    0.40
     cro
    0.38
     reefs
    0.38
     guarantees
    0.37
     uttering
    0.36
     imaginable
    0.36
    signals
    0.36
     преда
    0.35
     obvious
    0.35
     intensity
    0.35
    POSITIVE LOGITS
    orel
    0.44
     नॉलेज
    0.42
    氅
    0.41
    োরের
    0.39
     Continuation
    0.38
    ཟ
    0.38
    加坡
    0.37
    twilio
    0.37
    هدف
    0.37
     Subram
    0.36
    Act Density 0.000%

    No Known Activations