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

    Neuronpedia

    INDEX
    Explanations

    rather

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    essel
    -0.07
    Files
    -0.07
     cracks
    -0.06
    ollar
    -0.06
     melt
    -0.06
    razier
    -0.06
     단
    -0.06
    agini
    -0.06
    ometown
    -0.06
     komen
    -0.06
    POSITIVE LOGITS
    .txt
    0.07
     generosity
    0.06
     ساله
    0.06
    兴
    0.06
    _OBJECT
    0.06
    @implementation
    0.06
    악
    0.06
    _buff
    0.06
    _super
    0.06
    quent
    0.06
    Act Density 0.001%

    No Known Activations