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

    Neuronpedia

    INDEX
    Explanations

    task

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Laugh
    -0.07
    Md
    -0.06
    γω
    -0.06
    Luc
    -0.06
     lực
    -0.06
    ゞ
    -0.06
     devoid
    -0.06
     expres
    -0.06
    -vs
    -0.06
     jit
    -0.06
    POSITIVE LOGITS
     آهنگ
    0.06
     ActionTypes
    0.06
    _API
    0.06
    午
    0.06
    iments
    0.06
     birlik
    0.06
     цих
    0.06
     Rocks
    0.06
    [class
    0.06
    -images
    0.06
    Act Density 0.010%

    No Known Activations