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

    Neuronpedia

    INDEX
    Explanations

    terms related to emotional states and their implications in various contexts

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

    problems and solutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    -0.44
     Utiliz
    -0.42
     Mich
    -0.41
     endothelial
    -0.41
     interse
    -0.41
     utilizing
    -0.40
     ucc
    -0.40
     ujednoznacz
    -0.40
     Vish
    -0.40
     Hol
    -0.40
    POSITIVE LOGITS
     angst
    0.72
     puberty
    0.71
     amnesia
    0.65
     impunity
    0.60
     tabloid
    0.60
     boomers
    0.59
     Sabina
    0.58
     jargon
    0.58
    arkov
    0.58
    otene
    0.57
    Act Density 0.015%

    No Known Activations