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

    Neuronpedia

    INDEX
    Explanations

    Importance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     '('
    -0.07
     };
↵
↵
    -0.06
     다음과
    -0.06
     }
↵
↵
    -0.06
    ailability
    -0.06
     законодав
    -0.06
     žádné
    -0.06
    createCommand
    -0.06
    玲
    -0.06
    ;
↵
↵
    -0.06
    POSITIVE LOGITS
     hedef
    0.07
     Target
    0.07
    afa
    0.07
     timber
    0.06
    になり
    0.06
    lica
    0.06
     footage
    0.06
    ओ
    0.06
    ipheral
    0.06
    _tail
    0.06
    Act Density 0.238%

    No Known Activations