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

    Neuronpedia

    INDEX
    Explanations

    CK

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    忝
    -0.07
    酲
    -0.07
    焉
    -0.07
     total
    -0.07
     appear
    -0.07
    槃
    -0.07
    alo
    -0.07
     collectively
    -0.06
    ivor
    -0.06
    /U
    -0.06
    POSITIVE LOGITS
     childs
    0.08
    젯
    0.07
    .blocks
    0.07
     mesa
    0.07
     utiliser
    0.07
    blocks
    0.07
     exquisite
    0.07
    änder
    0.07
     __(
    0.07
    missão
    0.06
    Act Density 0.002%

    No Known Activations