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

    Neuronpedia

    INDEX
    Explanations

    winter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (CH
    -0.07
    华盛顿
    -0.07
    (Conv
    -0.07
     convicted
    -0.07
    Detroit
    -0.07
    etroit
    -0.07
    .bin
    -0.07
     Spike
    -0.07
     Dhabi
    -0.07
    袱
    -0.06
    POSITIVE LOGITS
     required
    0.07
    Selectable
    0.07
    wij
    0.06
    渫
    0.06
     El
    0.06
    ึ
    0.06
    ftype
    0.06
    Greetings
    0.06
    ,r
    0.06
    _ai
    0.06
    Act Density 0.029%

    No Known Activations