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

    Neuronpedia

    INDEX
    Explanations

    constructions indicating capability or possibility

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

    how can I

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    alakip
    -0.47
    ambién
    -0.47
     affari
    -0.43
     étoit
    -0.42
     belangrij
    -0.42
     pregunto
    -0.42
    tierra
    -0.42
    ientras
    -0.41
    errHandler
    -0.41
     Theore
    -0.41
    POSITIVE LOGITS
    esModule
    0.59
     ujednoznacz
    0.57
    windowFixed
    0.53
    
    0.52
    Smarty
    0.52
    Życiorys
    0.51
    RenderAtEndOf
    0.51
     consultato
    0.45
    FunctionFlags
    0.44
    如何
    0.43
    Act Density 0.014%

    No Known Activations