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

    Neuronpedia

    INDEX
    Explanations

    code and symbols in lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aldehydes
    0.79
     동물
    0.77
     lizards
    0.77
     ankles
    0.75
     kucing
    0.75
     ставак
    0.74
    ா
    0.74
    CheckingType
    0.74
     இயற்க
    0.73
     dodgy
    0.73
    POSITIVE LOGITS
    '
    1.14
    s
    1.05
    -
    1.00
     :
    0.92
     in
    0.88
    {
    0.88
    1
    0.87
    ]
    0.86
    )
    0.85
    $
    0.84
    Act Density 0.000%

    No Known Activations