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

    Neuronpedia

    INDEX
    Explanations

    limitations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     конце
    -0.07
     Created
    -0.07
    atabases
    -0.07
    _csv
    -0.07
    ’t
    -0.06
    -office
    -0.06
     vnode
    -0.06
    .translation
    -0.06
     پرس
    -0.06
     vacant
    -0.06
    POSITIVE LOGITS
    akash
    0.07
     yay
    0.07
    ')));↵
    0.06
    \s
    0.06
    くと
    0.06
    ussels
    0.06
     �
    0.06
    Reach
    0.06
    isay
    0.06
     xung
    0.06
    Act Density 0.003%

    No Known Activations