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

    Neuronpedia

    INDEX
    Explanations

    references to personal memories and nostalgia

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

    me demand varieties community

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     clos
    -0.43
    alei
    -0.41
    DeleteBehavior
    -0.41
    Życiorys
    -0.39
    ########.
    -0.39
    clos
    -0.36
    켭
    -0.36
    стки
    -0.36
    thun
    -0.34
    icago
    -0.34
    POSITIVE LOGITS
    occuper
    0.60
    NameInMap
    0.57
    BagConstraints
    0.52
     صوتيه
    0.47
    قایناقلار
    0.45
     ErrIntOverflow
    0.42
    клопе
    0.41
    NgModule
    0.41
    humanité
    0.40
    ambién
    0.39
    Act Density 0.023%

    No Known Activations