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

    Neuronpedia

    INDEX
    Explanations

    entryways

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gambling
    -0.08
    .frequency
    -0.08
    oung
    -0.08
    frequency
    -0.08
     Frequency
    -0.08
    .tools
    -0.07
    _ITER
    -0.07
     frequency
    -0.07
    'aurais
    -0.07
     GH
    -0.07
    POSITIVE LOGITS
     welcoming
    0.17
     സ്വാഗത
    0.16
     स्वागत
    0.15
    Entrance
    0.15
     welcome
    0.14
     Welcome
    0.14
     Entrance
    0.14
    欢迎
    0.14
    Welcome
    0.14
     entrance
    0.14
    Act Density 0.038%

    No Known Activations