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

    Neuronpedia

    INDEX
    Explanations

    exploring possibilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Editing
    -0.07
     derby
    -0.07
    drs
    -0.06
    _shift
    -0.06
    редел
    -0.06
    $fields
    -0.06
     narrow
    -0.06
     saldır
    -0.06
     "../../../
    -0.06
    -conscious
    -0.06
    POSITIVE LOGITS
    サイ
    0.07
     dobře
    0.07
    vertis
    0.07
     Vital
    0.06
    완
    0.06
     생
    0.06
     contenu
    0.06
    終
    0.06
     sabot
    0.06
     believable
    0.06
    Act Density 0.006%

    No Known Activations