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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FromNib
    -0.08
     �
    -0.07
     miło
    -0.07
    כנע
    -0.07
     NSStringFromClass
    -0.07
    �
    -0.07
     phản
    -0.07
    (curl
    -0.06
     mijn
    -0.06
    develop
    -0.06
    POSITIVE LOGITS
    周一
    0.07
     Usa
    0.07
    hawk
    0.07
    	util
    0.07
    蒜
    0.07
    累计
    0.06
     util
    0.06
    *scale
    0.06
     battling
    0.06
    _OPENGL
    0.06
    Act Density 0.005%

    No Known Activations