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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
     Brain
    -0.07
    mag
    -0.07
    אבא
    -0.07
    (count
    -0.07
    Dat
    -0.07
     Succ
    -0.07
    ประโย
    -0.07
    arendra
    -0.07
    مو
    -0.07
    POSITIVE LOGITS
    _SRC
    0.08
     Giới
    0.07
    עשייה
    0.07
    riday
    0.07
    _PROJECT
    0.07
    /////////////////////////////////////////////////////////////////////////////↵
    0.07
    _PS
    0.07
    .Low
    0.07
    _LOOP
    0.07
    _hi
    0.07
    Act Density 0.001%

    No Known Activations