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

    Neuronpedia

    INDEX
    Explanations

    Research without restrictions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aving
    -0.07
    .espresso
    -0.07
    ialias
    -0.07
    環
    -0.07
    ères
    -0.07
    อบรม
    -0.07
    _TOGGLE
    -0.07
    نامج
    -0.06
    /'.$
    -0.06
    _modal
    -0.06
    POSITIVE LOGITS
     Interestingly
    0.07
    网易
    0.07
    闽
    0.06
    (results
    0.06
    _UNITS
    0.06
     susceptibility
    0.06
    GetEnumerator
    0.06
    Comparer
    0.06
    izards
    0.06
     cuối
    0.06
    Act Density 0.004%

    No Known Activations