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

    Neuronpedia

    INDEX
    Explanations

    Code/data structures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defining
    -0.07
     Sustainable
    -0.07
    rne
    -0.06
    .Linked
    -0.06
    Es
    -0.06
    Filed
    -0.06
    على
    -0.06
    disc
    -0.06
     bl
    -0.06
    的名字
    -0.06
    POSITIVE LOGITS
    _DUMP
    0.07
    PTY
    0.07
     AAP
    0.07
    ට
    0.07
    �
    0.07
    AAP
    0.07
    生产总值
    0.07
    核电
    0.07
    装配
    0.07
    中断
    0.07
    Act Density 0.011%

    No Known Activations