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

    Neuronpedia

    INDEX
    Explanations

    Code/technical content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     {{↵
    -0.07
    rw
    -0.07
    정을
    -0.06
    ersen
    -0.06
     стены
    -0.06
     Jihad
    -0.06
    shapes
    -0.06
    BOX
    -0.06
     birkaç
    -0.06
     بسیاری
    -0.06
    POSITIVE LOGITS
    (ms
    0.07
    (header
    0.06
    (now
    0.06
    (cont
    0.06
    Cont
    0.06
    าต
    0.06
    .SDK
    0.06
    _Metadata
    0.06
    (g
    0.06
    (decimal
    0.06
    Act Density 0.000%

    No Known Activations