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

    Neuronpedia

    INDEX
    Explanations

    wall

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ú
    -0.06
     Computing
    -0.06
    <Car
    -0.06
     modes
    -0.06
     öğret
    -0.06
    exist
    -0.06
    Bu
    -0.06
    _proc
    -0.06
     sun
    -0.06
    _Err
    -0.06
    POSITIVE LOGITS
     """
↵
↵
    0.07
    olumn
    0.07
    $form
    0.07
     onSubmit
    0.07
     opens
    0.07
    الإنجليزية
    0.07
     halten
    0.07
     adulte
    0.06
    ]}"↵
    0.06
    agraph
    0.06
    Act Density 0.005%

    No Known Activations