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

    Neuronpedia

    INDEX
    Explanations

    Boost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UDGE
    -0.07
    _HEAP
    -0.07
     Rocky
    -0.07
    TAIL
    -0.06
    .abstract
    -0.06
     Royal
    -0.06
     phantom
    -0.06
    Oak
    -0.06
    measure
    -0.06
     familiar
    -0.06
    POSITIVE LOGITS
    ajaran
    0.07
    олнитель
    0.06
    indsay
    0.06
    abbage
    0.06
    ugo
    0.06
    ERRU
    0.06
     تومان
    0.06
    Encode
    0.06
     والتي
    0.06
    	add
    0.06
    Act Density 0.000%

    No Known Activations