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

    Neuronpedia

    INDEX
    Explanations

    specific identifiers or separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     innego
    0.50
    𝔬
    0.49
     aktivitas
    0.46
     logiciels
    0.46
     sauvage
    0.45
    ماء
    0.44
     tallest
    0.44
     aktivnosti
    0.44
     talleres
    0.43
    रिडोर
    0.43
    POSITIVE LOGITS
    0
    0.47
    }');
    0.45
    RA
    0.43
    限
    0.43
    atu
    0.42
    $
    0.42
    ENA
    0.42
    ably
    0.42
    $'
    0.41
    ẽ
    0.41
    Act Density 0.000%

    No Known Activations