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

    Neuronpedia

    INDEX
    Explanations

    salad

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    //----------------------------------------------------------------------------↵
    -0.08
    awe
    -0.07
    _slots
    -0.07
    彼女
    -0.06
     времени
    -0.06
    Mos
    -0.06
    ROPERTY
    -0.06
     Auschwitz
    -0.06
     losers
    -0.06
     induction
    -0.06
    POSITIVE LOGITS
     사람은
    0.06
    154
    0.06
     algum
    0.06
    (sec
    0.06
    (job
    0.06
    /dd
    0.06
    Carrier
    0.06
    WithContext
    0.06
    �
    0.05
    rál
    0.05
    Act Density 0.000%

    No Known Activations