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

    Neuronpedia

    INDEX
    Explanations

    Funding, influence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    kick
    -0.07
    stick
    -0.06
    _apply
    -0.06
    blob
    -0.06
    rectangle
    -0.06
     Spam
    -0.06
    Jump
    -0.06
     "!
    -0.06
    Fight
    -0.06
    _boxes
    -0.06
    POSITIVE LOGITS
     DevExpress
    0.07
    (varargin
    0.06
    ován
    0.06
     вваж
    0.06
    }_
    0.06
    itious
    0.06
     gep
    0.06
    ルフ
    0.06
     UIF
    0.06
     decir
    0.06
    Act Density 0.032%

    No Known Activations