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

    Neuronpedia

    INDEX
    Explanations

    Code and programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .spin
    -0.07
     VStack
    -0.07
     assign
    -0.06
     malign
    -0.06
    fortawesome
    -0.06
     criter
    -0.06
     налог
    -0.06
    udoku
    -0.06
     din
    -0.06
    Mech
    -0.06
    POSITIVE LOGITS
     motivating
    0.07
    -progress
    0.07
     Empresa
    0.06
    iễn
    0.06
     Antar
    0.06
     Statistical
    0.06
    ेष
    0.06
    /entities
    0.06
    iston
    0.06
    يلة
    0.06
    Act Density 0.018%

    No Known Activations