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

    Neuronpedia

    INDEX
    Explanations

    {

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olics
    -0.07
    otide
    -0.06
    ъ
    -0.06
    M
    -0.06
    duce
    -0.06
    _nb
    -0.06
    -fix
    -0.06
    illard
    -0.06
    чает
    -0.06
     MAG
    -0.06
    POSITIVE LOGITS
    /pl
    0.07
     `.
    0.06
    コード
    0.06
    collections
    0.06
     doctr
    0.06
    _APPRO
    0.06
    >Loading
    0.06
     галуз
    0.06
     itir
    0.06
     klíč
    0.06
    Act Density 0.001%

    No Known Activations