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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal digits in color codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    visory
    0.46
    df
    0.45
    ußer
    0.45
    bs
    0.44
    ada
    0.43
    udahkan
    0.43
    ta
    0.42
    ata
    0.41
    cached
    0.41
    et
    0.41
    POSITIVE LOGITS
    ﻨ
    0.64
    IDENT
    0.55
    ﻤ
    0.54
    ﺸ
    0.54
    OPER
    0.53
    ANS
    0.52
     INC
    0.52
    ACIÓN
    0.52
    ORDON
    0.52
    UGUST
    0.51
    Act Density 0.011%

    No Known Activations