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

    Neuronpedia

    INDEX
    Explanations

    words related to diseases, health conditions, and disasters where people get hurt.

    oai_token-act-pair · gemini-2.0-flash

    problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tvguidetime
    -0.73
    fjspx
    -0.73
    IsContent
    -0.72
    enterOuterAlt
    -0.69
    Eloquent
    -0.66
    queryInterface
    -0.66
    DockStyle
    -0.65
    WaitGroup
    -0.65
    исленность
    -0.64
    ItemBackground
    -0.64
    POSITIVE LOGITS
    Lähteet
    0.52
     způ
    0.48
    тельстве
    0.47
     způso
    0.47
     affect
    0.47
     hurt
    0.46
     administrativos
    0.46
     sarili
    0.45
    тельство
    0.45
     چیست
    0.45
    Act Density 1.883%

    No Known Activations