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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    系统
    -0.06
    .ModelForm
    -0.06
    Constant
    -0.06
     проведения
    -0.06
     Economy
    -0.06
     ISA
    -0.06
     озна
    -0.06
    .GetKey
    -0.06
     Pak
    -0.06
    (current
    -0.05
    POSITIVE LOGITS
    emplace
    0.07
    otos
    0.06
     p
    0.06
    Pl
    0.06
    olutely
    0.06
     glm
    0.06
    ويل
    0.06
     Holt
    0.06
    ution
    0.06
     selfie
    0.06
    Act Density 0.007%

    No Known Activations