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

    Neuronpedia

    INDEX
    Explanations

    email personalization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lazer
    -0.08
     braços
    -0.08
    _dtype
    -0.08
     الو
    -0.08
     وذلك
    -0.08
     الحم
    -0.08
     Princeton
    -0.07
    .Transport
    -0.07
     Dart
    -0.07
     وهذا
    -0.07
    POSITIVE LOGITS
    variables
    0.12
     substitutions
    0.12
     variables
    0.11
     placeholders
    0.11
     substitution
    0.10
     personalization
    0.10
     scripting
    0.10
     sustit
    0.10
    Variables
    0.10
    变量
    0.10
    Act Density 0.014%

    No Known Activations