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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    ="(
    -0.07
    rieving
    -0.07
    оч
    -0.07
    Ѽ
    -0.06
    _BEFORE
    -0.06
    ຄ
    -0.06
    羡
    -0.06
    .layouts
    -0.06
    קורס
    -0.06
    POSITIVE LOGITS
    也在
    0.07
     shooting
    0.07
    ]}↵
    0.07
     Det
    0.07
    实训
    0.06
     cord
    0.06
     shooter
    0.06
    礴
    0.06
    SUR
    0.06
    _surface
    0.06
    Act Density 0.003%

    No Known Activations