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

    Neuronpedia

    INDEX
    Explanations

    ^

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (pl
    -0.07
    시키
    -0.07
     اولین
    -0.07
    basic
    -0.07
    .example
    -0.07
     ]).
    -0.07
     seal
    -0.07
    _b
    -0.07
     resultMap
    -0.06
     gran
    -0.06
    POSITIVE LOGITS
    Void
    0.06
    abilia
    0.06
    .ImageField
    0.06
    ária
    0.06
     APPRO
    0.06
     Народ
    0.05
     Yardım
    0.05
    >\↵
    0.05
     Tây
    0.05
    Česk
    0.05
    Act Density 0.000%

    No Known Activations