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

    Neuronpedia

    INDEX
    Explanations

    activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soudu
    -0.07
     ((((
    -0.06
    COD
    -0.06
    =~
    -0.06
     Wife
    -0.06
    bonus
    -0.06
     bý
    -0.06
    τους
    -0.06
     ﻣ
    -0.06
     utils
    -0.06
    POSITIVE LOGITS
     activities
    0.07
     actividades
    0.07
    让我
    0.07
    Lic
    0.06
    TRUE
    0.06
    plain
    0.06
    /',↵
    0.06
    LOWER
    0.06
    рив
    0.06
    err
    0.06
    Act Density 0.049%

    No Known Activations