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

    Neuronpedia

    INDEX
    Explanations

    Code and functions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rak
    -0.07
    26
    -0.07
    replacement
    -0.07
    spa
    -0.06
    脑
    -0.06
    [d
    -0.06
     Churchill
    -0.06
    -green
    -0.06
     Prague
    -0.06
     church
    -0.06
    POSITIVE LOGITS
    ilim
    0.07
    .getDate
    0.07
     evenly
    0.07
    rganization
    0.06
    ETwitter
    0.06
    MethodBeat
    0.06
    .TrimSpace
    0.06
    .Token
    0.06
    "data
    0.06
    .AutoScale
    0.06
    Act Density 0.102%

    No Known Activations