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

    Neuronpedia

    INDEX
    Explanations

    Code/Configuration snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    alted
    -0.07
    ////////////////////////////////////////////////
    -0.06
    macro
    -0.06
     overrides
    -0.06
    arf
    -0.06
    .green
    -0.06
     disrupting
    -0.06
    .transaction
    -0.06
    _team
    -0.06
     Judges
    -0.06
    POSITIVE LOGITS
     Catalonia
    0.07
    رز
    0.07
     prostitut
    0.07
     applicable
    0.06
    _nn
    0.06
    _unused
    0.06
     divergence
    0.06
    Appear
    0.06
     Betty
    0.06
    구
    0.06
    Act Density 0.000%

    No Known Activations