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

    Neuronpedia

    INDEX
    Explanations

    Floors and surfaces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ISNI
    -0.89
     Eſ
    -0.84
     Monfieur
    -0.82
     Efq
    -0.82
    CloseOperation
    -0.81
     ―――――
    -0.80
     Theſe
    -0.79
     Inflate
    -0.79
     iſt
    -0.78
     Reſ
    -0.78
    POSITIVE LOGITS
    newswire
    0.37
    ----</
    0.37
    I
    0.34
    外部リンク
    0.33
     e
    0.33
    khidmatan
    0.32
     د
    0.32
    ↵
    0.31
     del
    0.31
     simplicité
    0.31
    Act Density 0.015%

    No Known Activations