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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tikang
    -1.34
     Houſe
    -1.34
     itſelf
    -1.34
     Theſe
    -1.33
     Reſ
    -1.24
     myſelf
    -1.23
     photolibrary
    -1.21
    ſelf
    -1.20
     Anſ
    -1.19
     Diſ
    -1.17
    POSITIVE LOGITS
     (
    1.52
     [
    0.98
    (
    0.86
     ('
    0.73
     ((
    0.69
     we
    0.66
     (!
    0.65
    "
    0.64
     
    0.63
     a
    0.62
    Act Density 0.059%

    No Known Activations