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

    Neuronpedia

    INDEX
    Explanations

    article snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -0.81
    
    -0.79
     doubtnut
    -0.75
     myſelf
    -0.75
     resourceCulture
    -0.73
    posedge
    -0.73
    OGND
    -0.71
     للمعارف
    -0.71
     ―――――
    -0.71
     Jefus
    -0.71
    POSITIVE LOGITS
    Viitteet
    0.54
    medriver
    0.47
    olo
    0.47
    ↵↵
    0.44
     (
    0.44
     
    0.43
    出版年
    0.42
     multiple
    0.42
    stri
    0.41
     a
    0.41
    Act Density 0.005%

    No Known Activations