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

    Neuronpedia

    INDEX
    Explanations

    numbers and statistical information

    oai_token-act-pair · gemini-2.0-flash

    Romanian language tokens starting with a specific pattern

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

    Statistical data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ineno
    -0.59
    LabelTagHelper
    -0.57
    #
    -0.56
    WebVitals
    -0.54
    xase
    -0.53
    DockStyle
    -0.53
     đơn
    -0.51
    PerformLayout
    -0.50
    INCT
    -0.50
    permum
    -0.50
    POSITIVE LOGITS
     veau
    0.60
     îna
    0.54
     învă
    0.54
     câte
    0.53
     solito
    0.52
     åt
    0.52
     vreme
    0.51
     Tacitus
    0.51
     Exacts
    0.50
     gostaria
    0.50
    Act Density 3.737%

    No Known Activations