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

    Neuronpedia

    INDEX
    Explanations

    Errors and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    007
    -0.06
    essional
    -0.06
     měsí
    -0.06
     ב
    -0.06
    ียวก
    -0.06
     якого
    -0.06
     генера
    -0.06
     dau
    -0.06
    ̉
    -0.06
     kara
    -0.06
    POSITIVE LOGITS
    .equ
    0.07
    сы
    0.06
     JsonRequestBehavior
    0.06
     reimb
    0.06
    enary
    0.06
    )))↵↵
    0.06
    						
↵
    0.06
    _PWM
    0.06
    "},
↵
    0.06
    knife
    0.06
    Act Density 0.002%

    No Known Activations