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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    чу
    -0.08
    英文
    -0.07
    环
    -0.07
     �
    -0.07
    �
    -0.07
     genders
    -0.06
    090
    -0.06
    Wave
    -0.06
     Essential
    -0.06
     zas
    -0.06
    POSITIVE LOGITS
     Περι
    0.07
    enci
    0.06
     grap
    0.06
    “
    0.06
     calculations
    0.06
    (goal
    0.06
     "/"↵
    0.06
    .gpu
    0.06
    _ComCallableWrapper
    0.06
     '*.
    0.06
    Act Density 0.026%

    No Known Activations