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

    Neuronpedia

    INDEX
    Explanations

    toxic foods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ンディ
    -0.07
     bursts
    -0.06
     FIRE
    -0.06
    -des
    -0.06
    .simps
    -0.06
     parity
    -0.06
     Spr
    -0.06
    Wr
    -0.06
    iculty
    -0.06
    sealed
    -0.06
    POSITIVE LOGITS
    grupo
    0.07
    Further
    0.06
     отказ
    0.06
    õ
    0.06
    建立
    0.06
    대표
    0.06
    [NUM
    0.06
    ategorie
    0.06
    _projects
    0.06
     chrono
    0.06
    Act Density 0.006%

    No Known Activations