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

    Neuronpedia

    INDEX
    Explanations

    invite

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     distinctions
    -0.09
     distinction
    -0.08
     দক্ষ
    -0.08
     parse
    -0.08
    _PARSE
    -0.08
    析
    -0.08
     distinguishes
    -0.08
     திற
    -0.08
    esk
    -0.08
     القول
    -0.08
    POSITIVE LOGITS
     bottled
    0.08
    oreferrer
    0.08
    _pin
    0.08
     foam
    0.08
    риз
    0.08
     हुनेछ
    0.08
     Rechnung
    0.07
    opol
    0.07
    mah
    0.07
     finalized
    0.07
    Act Density 0.014%

    No Known Activations