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
     sunset
    -0.08
    461
    -0.07
    -function
    -0.07
    ันน
    -0.07
    atonin
    -0.06
    uario
    -0.06
    isbury
    -0.06
    	mov
    -0.06
    ские
    -0.06
    theory
    -0.06
    POSITIVE LOGITS
    _LOG
    0.07
    enge
    0.07
    .RE
    0.07
    赏
    0.06
    ~":"
    0.06
    .ge
    0.06
    軽
    0.06
     Ticaret
    0.06
    链接
    0.06
    (bean
    0.06
    Act Density 0.060%

    No Known Activations