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

    Neuronpedia

    INDEX
    Explanations

    turn

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     leukemia
    -0.07
     QA
    -0.07
     DIE
    -0.06
     PIE
    -0.06
    pj
    -0.06
    _PERSON
    -0.06
    $j
    -0.06
     پروژه
    -0.06
     '*'
    -0.06
    ③
    -0.06
    POSITIVE LOGITS
     disabling
    0.06
    balls
    0.06
    �
    0.06
    lesai
    0.06
     síd
    0.06
    ossil
    0.06
     asking
    0.06
    cum
    0.06
     slun
    0.06
    ippo
    0.06
    Act Density 0.002%

    No Known Activations