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

    Neuronpedia

    INDEX
    Explanations

    code and data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kč
    -0.07
    داری
    -0.07
    amat
    -0.07
    .performance
    -0.06
     dessert
    -0.06
    AWN
    -0.06
    stripe
    -0.06
    “If
    -0.06
     heuristic
    -0.06
     Harlem
    -0.06
    POSITIVE LOGITS
     Converter
    0.07
     anlaş
    0.07
     Constraint
    0.07
     getUsername
    0.07
     Wolfgang
    0.06
    cular
    0.06
     executed
    0.06
    _SCREEN
    0.06
     IsValid
    0.06
     ###
    0.06
    Act Density 0.056%

    No Known Activations