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

    Neuronpedia

    INDEX
    Explanations

    Example

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;|
    -0.07
    ิ
    -0.06
     underscore
    -0.06
     snapchat
    -0.06
    ->↵
    -0.06
    entities
    -0.06
     Tcl
    -0.06
     }],↵
    -0.06
    thetic
    -0.06
    rases
    -0.06
    POSITIVE LOGITS
     dağ
    0.07
    \Storage
    0.06
     několik
    0.06
    울
    0.06
    upid
    0.06
    (col
    0.06
     bulletin
    0.06
    0.06
     Financial
    0.06
    .exceptions
    0.06
    Act Density 0.002%

    No Known Activations