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

    Neuronpedia

    INDEX
    Explanations

    study

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bitir
    -0.06
    elijke
    -0.06
    ики
    -0.06
    ічна
    -0.06
     ż
    -0.06
     basics
    -0.06
     키
    -0.06
    ayne
    -0.06
     ابتد
    -0.06
     مك
    -0.06
    POSITIVE LOGITS
     study
    0.07
     Officer
    0.07
    forums
    0.07
     PLUS
    0.06
    _init
    0.06
     Hitler
    0.06
     Researchers
    0.06
    _Window
    0.06
    Founded
    0.06
     slam
    0.06
    Act Density 0.032%

    No Known Activations