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

    Neuronpedia

    INDEX
    Explanations

    plus sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ….
    -0.07
    Вы
    -0.07
     их
    -0.06
     AppComponent
    -0.06
     dia
    -0.06
     їм
    -0.06
     histo
    -0.06
     LJ
    -0.06
     brewery
    -0.06
     fourteen
    -0.06
    POSITIVE LOGITS
     +
    0.07
     педагог
    0.06
     add
    0.06
    栏
    0.06
     případě
    0.06
     раздел
    0.06
    ellation
    0.06
    _Trans
    0.06
    .Dto
    0.06
     haystack
    0.06
    Act Density 0.004%

    No Known Activations