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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (size
    -0.07
     INIT
    -0.06
    _Val
    -0.06
    .FormStartPosition
    -0.06
     Executes
    -0.06
     descr
    -0.06
     رفت
    -0.06
    ('{}
    -0.06
    (core
    -0.06
     Checking
    -0.06
    POSITIVE LOGITS
    ��
    0.06
    .appendChild
    0.06
    ство
    0.06
    .env
    0.06
    icens
    0.06
     diplomats
    0.06
    .isHidden
    0.06
     defended
    0.06
     violated
    0.06
    irms
    0.05
    Act Density 0.002%

    No Known Activations