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

    Neuronpedia

    INDEX
    Explanations

    platonic relationships

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    قت
    -0.07
    arel
    -0.06
    גרפי
    -0.06
    屉
    -0.06
    conf
    -0.06
    zug
    -0.06
     pouch
    -0.06
     file
    -0.06
    (chan
    -0.06
    -nine
    -0.06
    POSITIVE LOGITS
    tick
    0.07
    重磅
    0.07
    MULT
    0.07
     EVERY
    0.07
     Hilton
    0.06
     ليست
    0.06
    _HP
    0.06
    .eval
    0.06
     no
    0.06
    VA
    0.06
    Act Density 0.095%

    No Known Activations