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

    Neuronpedia

    INDEX
    Explanations

    phrases that express potentiality and existential reflection

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

    that has never been

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.60
    Diweddarwch
    -0.58
    Autoritní
    -0.57
     referrerpolicy
    -0.55
    OGND
    -0.51
     Italijanski
    -0.50
     հղումներ
    -0.47
     Administrativna
    -0.47
    UnusedPrivate
    -0.46
    cerpt
    -0.45
    POSITIVE LOGITS
     useAppContext
    0.44
    retanto
    0.41
    gdx
    0.40
     Nachbarn
    0.40
     fué
    0.38
     Realität
    0.35
     Inseln
    0.34
    .';
    0.34
    BoxShadow
    0.34
    .',
    0.34
    Act Density 0.029%

    No Known Activations