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

    Neuronpedia

    INDEX
    Explanations

    Japanese topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ак
    -0.07
    .ax
    -0.07
     サ
    -0.07
     nik
    -0.06
     raining
    -0.06
    rides
    -0.06
     Type
    -0.06
     combined
    -0.06
     cheating
    -0.06
     polygon
    -0.06
    POSITIVE LOGITS
    ReadWrite
    0.08
    _ssl
    0.07
     endings
    0.07
     filesystem
    0.07
     inputs
    0.06
     driveway
    0.06
    Digits
    0.06
    eygamber
    0.06
    输入
    0.06
    .cljs
    0.06
    Act Density 0.000%

    No Known Activations