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

    Neuronpedia

    INDEX
    Explanations

    Code and website snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ThroughAttribute
    -0.66
     Италијани
    -0.60
    xodo
    -0.57
    ̈́
    -0.56
    исленность
    -0.56
     gynhyrchwyd
    -0.53
    енча
    -0.53
    ServerName
    -0.53
     referenties
    -0.52
    nezeu
    -0.51
    POSITIVE LOGITS
    //
    0.65
    脚注の使い方
    0.59
    CreateMap
    0.54
    IsPostBack
    0.52
    クタ
    0.51
    prim
    0.50
     समीक्षाओं
    0.50
     ic
    0.49
     prime
    0.49
     pri
    0.47
    Act Density 0.000%

    No Known Activations