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

    Neuronpedia

    INDEX
    Explanations

    significant phrases and titles related to creativity or personal expression

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

    Preceding words of "of" or "ends"

    np_acts-logits-general · gemini-2.0-flash

    ends of justice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }}$}
    -0.89
    Personendaten
    -0.87
     Efq
    -0.86
     "..\..\..\
    -0.85
    InitVars
    -0.85
     الرياضيه
    -0.84
     "..\..\
    -0.83
    tagext
    -0.81
     jsPsych
    -0.80
     purpoſe
    -0.80
    POSITIVE LOGITS
     #
    0.63
     __
    0.61
    ...
    0.57
    …
    0.52
    !
    0.50
    theim
    0.50
     appunto
    0.50
    #
    0.50
     Frist
    0.48
     _
    0.47
    Act Density 0.142%

    No Known Activations