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

    Neuronpedia

    INDEX
    Explanations

    code and URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    strcpy
    -0.06
    _conditions
    -0.06
    cyan
    -0.06
    pwd
    -0.06
    categories
    -0.06
     matrix
    -0.06
     yahoo
    -0.06
    tanggal
    -0.06
     perceive
    -0.06
     programmes
    -0.06
    POSITIVE LOGITS
     sibling
    0.07
    ْم
    0.07
     gặp
    0.07
     �
    0.06
    グル
    0.06
     ช
    0.06
     دنبال
    0.06
     Albuquerque
    0.06
    алася
    0.06
    apsulation
    0.06
    Act Density 0.000%

    No Known Activations