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

    Neuronpedia

    INDEX
    Explanations

    Tasks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    otope
    -0.07
    _DOMAIN
    -0.06
    $a
    -0.06
     Reuters
    -0.06
     Continuing
    -0.06
    _real
    -0.06
     Honolulu
    -0.06
    weapon
    -0.06
     iterator
    -0.06
     instructors
    -0.06
    POSITIVE LOGITS
     ^{}
    0.08
     veel
    0.07
    _campaign
    0.07
     Lindsey
    0.06
     강
    0.06
     Salv
    0.06
     Fay
    0.06
     Jaw
    0.06
     Rakou
    0.06
     Pick
    0.06
    Act Density 0.130%

    No Known Activations