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

    Neuronpedia

    INDEX
    Explanations

    Normal sentences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $db
    -0.07
    'on
    -0.06
    "]=$
    -0.06
    těz
    -0.06
    егист
    -0.06
     sotto
    -0.06
    _features
    -0.06
    도
    -0.06
     csrf
    -0.06
    ’on
    -0.06
    POSITIVE LOGITS
     Bryce
    0.07
     functional
    0.07
     internal
    0.07
    <bool
    0.06
     Mini
    0.06
     councill
    0.06
     perpetual
    0.06
     zar
    0.06
    (paths
    0.06
     EAR
    0.06
    Act Density 0.000%

    No Known Activations