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

    Neuronpedia

    INDEX
    Explanations

    Par

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     heed
    -0.06
    Snackbar
    -0.06
    /functions
    -0.06
    neys
    -0.05
    (action
    -0.05
     Ai
    -0.05
    .space
    -0.05
    proxy
    -0.05
     Kennedy
    -0.05
    Initially
    -0.05
    POSITIVE LOGITS
    Par
    0.08
     başlamış
    0.07
     tables
    0.07
    ับปร
    0.07
     �
    0.07
     Phar
    0.07
     нез
    0.07
     impover
    0.07
     Tables
    0.07
    _PRIV
    0.07
    Act Density 0.018%

    No Known Activations