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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ');//
    -0.07
    _ic
    -0.07
    Job
    -0.07
    .hours
    -0.07
    ruc
    -0.06
    Road
    -0.06
     conceive
    -0.06
    那麼
    -0.06
     !↵
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    不断完善
    0.07
    Ⲅ
    0.07
    為
    0.07
    bagai
    0.07
    为
    0.07
     '
    0.06
    낳
    0.06
    iameter
    0.06
    ежду
    0.06
    edere
    0.06
    Act Density 0.020%

    No Known Activations