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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating simplicity or straightforwardness

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

    simple explanation or common name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    enumii
    -0.41
    lieri
    -0.38
     doet
    -0.37
    󠁣
    -0.36
     laufen
    -0.36
     herunterladen
    -0.35
     angelegt
    -0.35
     parallels
    -0.34
    なんて
    -0.34
    走去
    -0.33
    POSITIVE LOGITS
    Personendaten
    0.67
    ConstraintMaker
    0.66
    ]")]
    0.62
    Simply
    0.60
     autorytatywna
    0.58
    simply
    0.56
     jsPsych
    0.56
    ⤹
    0.55
    providedIn
    0.54
    DoubleQuotes
    0.54
    Act Density 0.053%

    No Known Activations