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

    Neuronpedia

    INDEX
    Explanations

    Slip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    drž
    -0.33
    kloped
    -0.31
    ImageContext
    -0.31
    例文帳に追加
    -0.31
    abcdefghijklmnop
    -0.31
    kla
    -0.30
    nes
    -0.30
    からです
    -0.30
     osv
    -0.29
    ium
    -0.29
    POSITIVE LOGITS
    webElementXpaths
    0.73
    ValueStyle
    0.70
    Molecular
    0.68
     Molecular
    0.68
     يتيمه
    0.66
     gynhyrchwyd
    0.66
     Secret
    0.65
    ftance
    0.64
    ^(@)
    0.62
    StoryboardSegue
    0.62
    Act Density 0.156%

    No Known Activations