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

    Neuronpedia

    INDEX
    Explanations

    Temple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nets
    -0.06
    arend
    -0.06
    ohen
    -0.06
    층의
    -0.06
     організа
    -0.06
     seinen
    -0.06
    encers
    -0.06
     lk
    -0.06
    ْه
    -0.06
     catast
    -0.06
    POSITIVE LOGITS
    148
    0.07
     happy
    0.07
     damage
    0.07
     Damage
    0.07
    110
    0.07
    食
    0.07
    type
    0.07
    alogy
    0.06
    160
    0.06
     katılım
    0.06
    Act Density 0.001%

    No Known Activations