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

    Neuronpedia

    INDEX
    Explanations

    Mel/EL

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _inter
    -0.07
     Formation
    -0.07
    -controller
    -0.07
    Loader
    -0.07
    _iter
    -0.07
    _button
    -0.07
     acquired
    -0.06
    빌
    -0.06
     Hidden
    -0.06
    _wire
    -0.06
    POSITIVE LOGITS
     CHK
    0.06
    .parentNode
    0.06
     anak
    0.06
     mysl
    0.06
     >>↵↵
    0.06
    ilog
    0.06
    реж
    0.06
     fright
    0.06
    .getNext
    0.06
    Jess
    0.06
    Act Density 0.002%

    No Known Activations