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

    Neuronpedia

    INDEX
    Explanations

    suggestions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    draulic
    -0.07
    ﳋ
    -0.07
    粢
    -0.07
    卫健
    -0.07
     Comput
    -0.07
    𐭍
    -0.07
    sistência
    -0.06
     relies
    -0.06
     rhetorical
    -0.06
    ﺇ
    -0.06
    POSITIVE LOGITS
     omission
    0.07
     unanimous
    0.07
    joined
    0.07
     Rover
    0.07
    ロック
    0.07
    .agent
    0.07
    :error
    0.07
     cortex
    0.07
    ouncil
    0.07
     smoker
    0.06
    Act Density 0.074%

    No Known Activations