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

    Neuronpedia

    INDEX
    Explanations

    Descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (int
    -0.06
    -opening
    -0.06
     Theresa
    -0.06
     ese
    -0.06
     felt
    -0.06
     provision
    -0.06
     pretended
    -0.06
    CRET
    -0.06
    避
    -0.06
    (choice
    -0.05
    POSITIVE LOGITS
    _SDK
    0.07
    代理
    0.07
    άλυ
    0.07
    asyarak
    0.07
     MQ
    0.07
    pq
    0.06
     gr
    0.06
    getStatusCode
    0.06
     firmalar
    0.06
    objective
    0.06
    Act Density 0.019%

    No Known Activations