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

    Neuronpedia

    INDEX
    Explanations

    approach to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ዘዴ
    0.53
    vorsch
    0.52
     avancé
    0.52
     metoda
    0.52
    respuesta
    0.52
    sprecher
    0.51
     consejo
    0.50
     Agregar
    0.50
     লেখক
    0.50
     opge
    0.50
    POSITIVE LOGITS
    is
    0.75
    :
    0.71
    ,
    0.58
    ability
    0.49
    ﾇ
    0.45
    メント
    0.45
     gereken
    0.44
    in
    0.44
    ную
    0.44
     taken
    0.43
    Act Density 0.022%

    No Known Activations