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

    Neuronpedia

    INDEX
    Explanations

    ال

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Headers
    -0.06
     fails
    -0.06
     Parks
    -0.06
     hoch
    -0.06
    Syn
    -0.06
     {}",
    -0.06
    $b
    -0.06
     perme
    -0.06
    ]);↵↵
    -0.06
     sails
    -0.06
    POSITIVE LOGITS
    ạ
    0.07
     hid
    0.06
    .semantic
    0.06
     Dere
    0.06
    lédl
    0.06
     hk
    0.06
     Ot
    0.06
    _GRP
    0.06
     universal
    0.06
    .Raise
    0.06
    Act Density 0.004%

    No Known Activations