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

    Neuronpedia

    INDEX
    Explanations

    phrases related to uncertainty or variability in actions or feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    also, not, vary, is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.65
    CloseOperation
    -0.57
     Wicidata
    -0.57
     informée
    -0.57
    RegressionTest
    -0.56
    orianCalendar
    -0.54
     snippetHide
    -0.54
    AndEndTag
    -0.53
    Portail
    -0.51
    IVEREF
    -0.50
    POSITIVE LOGITS
     therefrom
    0.35
     demikian
    0.31
     venuto
    0.31
     andato
    0.31
    SEMICOLON
    0.31
    ,:),
    0.31
     katanya
    0.30
    pin
    0.30
    日から
    0.30
     hefyd
    0.29
    Act Density 0.041%

    No Known Activations