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

    Neuronpedia

    INDEX
    Explanations

    MIT license, github

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ный
    -0.07
     Roads
    -0.07
     Winston
    -0.07
    Ins
    -0.07
    ۲۸
    -0.07
    28
    -0.07
    .Singleton
    -0.07
    compact
    -0.07
    inp
    -0.07
    .showToast
    -0.06
    POSITIVE LOGITS
     krij
    0.06
     由
    0.06
    ्रण
    0.06
     nắm
    0.06
     출시
    0.06
    elp
    0.06
    elsing
    0.06
    _MET
    0.06
     Лі
    0.06
     Swarm
    0.06
    Act Density 0.004%

    No Known Activations