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

    Neuronpedia

    INDEX
    Explanations

    detailed information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ੫
    0.53
    сли
    0.51
    ам
    0.50
    ્યાં
    0.50
    âmb
    0.50
     della
    0.49
     terecht
    0.49
    льної
    0.48
    Ꮵ
    0.48
    ﻼ
    0.48
    POSITIVE LOGITS
     Warna
    0.40
     Wet
    0.38
     Color
    0.38
     Milk
    0.37
    দেশের
    0.37
    Rüyada
    0.37
    ails
    0.37
    Wet
    0.36
    PREC
    0.36
    돕
    0.36
    Act Density 0.000%

    No Known Activations