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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kindly
    -0.07
    便利
    -0.07
    ��
    -0.07
     umożli
    -0.06
    陉
    -0.06
     GitHub
    -0.06
    TabIndex
    -0.06
    orean
    -0.06
    .alert
    -0.06
    受贿
    -0.06
    POSITIVE LOGITS
    ]*
    0.07
     Music
    0.06
    ivals
    0.06
    storage
    0.06
    ，在
    0.06
    滾
    0.06
     ripping
    0.06
    '}↵↵
    0.06
     Elem
    0.06
     Josh
    0.06
    Act Density 0.002%

    No Known Activations