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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pisc
    -0.06
     культури
    -0.06
    _ATT
    -0.06
    _sc
    -0.06
    erman
    -0.06
    居
    -0.06
    ійської
    -0.06
     правило
    -0.06
    طلق
    -0.06
    compan
    -0.06
    POSITIVE LOGITS
     činnosti
    0.07
     Excellent
    0.07
    cene
    0.07
     retrieve
    0.06
    (random
    0.06
     RuntimeError
    0.06
     obsess
    0.06
     Numeric
    0.06
    _Source
    0.06
    oq
    0.06
    Act Density 0.136%

    No Known Activations