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

    Neuronpedia

    INDEX
    Explanations

    institutions and resources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     =
↵
    -0.07
    ोस
    -0.07
    interested
    -0.07
    Width
    -0.06
    trip
    -0.06
    VV
    -0.06
     +
↵
    -0.06
    ندق
    -0.06
    -0.06
    Serializable
    -0.06
    POSITIVE LOGITS
     illusions
    0.07
     profiling
    0.06
    .appcompat
    0.06
    -pattern
    0.06
     책
    0.06
     affirm
    0.06
    /gpl
    0.06
    	namespace
    0.06
    arent
    0.06
    _EXTERN
    0.06
    Act Density 0.632%

    No Known Activations