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

    Neuronpedia

    INDEX
    Explanations

    inactivation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     powerhouse
    -0.07
    _power
    -0.07
    뫼
    -0.07
    莠
    -0.07
     MaterialApp
    -0.07
    הליכ
    -0.07
    מומ
    -0.07
     Benchmark
    -0.07
    (Stack
    -0.07
    (pixel
    -0.06
    POSITIVE LOGITS
    atory
    0.07
     ngăn
    0.07
    Mounted
    0.07
    讱
    0.06
    underline
    0.06
     obedient
    0.06
    AZE
    0.06
     форма
    0.06
    𝚑
    0.06
    父親
    0.06
    Act Density 0.077%

    No Known Activations