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

    Neuronpedia

    INDEX
    Explanations

    radio stations and associated words

    oai_token-act-pair · gemini-2.0-flash

    terms related to radio stations

    np_token-act-pair-logits · gpt-4o-mini

    radio stations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.60
     Efq
    -0.57
     Monfieur
    -0.54
     himſelf
    -0.50
     상세
    -0.49
     Riproduzione
    -0.48
     pleaſure
    -0.48
    sträger
    -0.48
    allible
    -0.47
    GEBURTSDATUM
    -0.47
    POSITIVE LOGITS
     سكانية
    0.58
    awtextra
    0.52
    omet
    0.52
    tagHelperRunner
    0.51
     Numerade
    0.50
    Дереккөздер
    0.50
    homonymie
    0.50
     ligiloj
    0.48
    HomeAsUpEnabled
    0.46
    antMatchers
    0.46
    Act Density 1.305%

    No Known Activations