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

    Neuronpedia

    INDEX
    Explanations

    other

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ിലാണ്
    0.84
    യിലാണ്
    0.78
    olojik
    0.75
     wobei
    0.73
    entgen
    0.73
    েশ
    0.71
     때문이다
    0.70
    alada
    0.69
    avasena
    0.68
    ॅक
    0.68
    POSITIVE LOGITS
     other
    7.17
    other
    6.48
    Other
    6.11
     Other
    6.08
     других
    5.94
     другие
    5.89
     andere
    5.85
     otros
    5.77
     autres
    5.75
    其他
    5.75
    Act Density 1.911%

    No Known Activations