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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks following complete thoughts or clauses

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

    describing state or characteristic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fırs
    -0.43
     lancement
    -0.40
     vœ
    -0.40
     jugement
    -0.39
     feroit
    -0.39
     chargement
    -0.38
     The
    -0.38
     légitime
    -0.37
     desplazamiento
    -0.37
     contactez
    -0.36
    POSITIVE LOGITS
    ftagPool
    0.85
    ⟬
    0.81
    tvguidetime
    0.78
     nonatomic
    0.77
     ivelany
    0.74
     Chwiliwch
    0.68
     Савезне
    0.68
    IntoConstraints
    0.68
     للاسماء
    0.68
    __*/
    0.67
    Act Density 0.037%

    No Known Activations