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

    Neuronpedia

    INDEX
    Explanations

    Detection and electronic work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Auf
    -0.06
    _checked
    -0.06
     compensated
    -0.06
     belirt
    -0.06
    upported
    -0.06
    \model
    -0.06
     HelloWorld
    -0.06
    ITIVE
    -0.06
    ่วน
    -0.06
     помощью
    -0.06
    POSITIVE LOGITS
    irteen
    0.07
    'elle
    0.07
    uffman
    0.07
    aligned
    0.06
     discrim
    0.06
     Digit
    0.06
     fantasy
    0.06
     звичай
    0.06
    关系
    0.06
    _ram
    0.06
    Act Density 0.254%

    No Known Activations