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

    Neuronpedia

    INDEX
    Explanations

    Klingon or ICMP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    NotBlank
    0.53
     as
    0.49
    Financial
    0.46
    Bloomberg
    0.46
     for
    0.45
    ing
    0.44
     have
    0.44
     একদম
    0.44
     całkow
    0.43
     ")
    0.43
    POSITIVE LOGITS
     Hombre
    0.54
     Midlands
    0.52
     Modena
    0.52
    قاب
    0.51
     Buc
    0.50
     Soy
    0.48
     Modelo
    0.48
     Ventil
    0.48
     Toutes
    0.47
     moat
    0.47
    Act Density 0.001%

    No Known Activations