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

    Neuronpedia

    INDEX
    Explanations

    legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    controls
    -0.07
     Phillips
    -0.07
    TEXT
    -0.07
     =$
    -0.06
     Bach
    -0.06
    args
    -0.06
     Santos
    -0.06
    Hamilton
    -0.06
    specified
    -0.06
    authors
    -0.06
    POSITIVE LOGITS
    ิด
    0.07
     resent
    0.07
    تیجه
    0.07
     '%$
    0.07
     flashback
    0.07
     khỏ
    0.06
    ().__
    0.06
    ีการ
    0.06
     �
    0.06
    _SHADOW
    0.06
    Act Density 0.022%

    No Known Activations