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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     louder
    -0.08
     статус
    -0.08
     interceptor
    -0.07
     incremental
    -0.07
    .setHeader
    -0.06
     sont
    -0.06
     taxpayer
    -0.06
     searching
    -0.06
     DWC
    -0.06
     чер
    -0.06
    POSITIVE LOGITS
     Native
    0.07
    expand
    0.06
     sexuality
    0.06
    "While
    0.06
    ΐ
    0.06
     rumored
    0.06
     nichž
    0.06
    봐
    0.06
    handling
    0.06
    female
    0.06
    Act Density 0.072%

    No Known Activations