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

    Neuronpedia

    INDEX
    Explanations

    expressions of desire or preference

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

    expressing desire or suggestion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.68
    //
    -0.50
    EFIAPI
    -0.49
     ComVisible
    -0.48
     Autorizaciones
    -0.48
     ponieważ
    -0.45
    uxxxx
    -0.44
     hermosas
    -0.44
    IContainer
    -0.44
    mektedir
    -0.44
    POSITIVE LOGITS
     outta
    0.53
     Aussie
    0.49
    wiliwch
    0.48
     Vgl
    0.47
    りゃ
    0.46
    iels
    0.45
     somethin
    0.45
    aughey
    0.44
     talkin
    0.44
    umptive
    0.44
    Act Density 0.014%

    No Known Activations