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

    Neuronpedia

    INDEX
    Explanations

    repeated phrases related to physical locations or spaces

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

    words ending in "es"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Portail
    -0.50
     africain
    -0.47
    DebuggerStep
    -0.46
    gyű
    -0.45
     HFILL
    -0.43
     StringIO
    -0.43
     Američ
    -0.43
     numérique
    -0.43
     OnClickListener
    -0.42
    السكان
    -0.42
    POSITIVE LOGITS
     فريبيس
    0.47
     CommonModule
    0.46
    ン
    0.45
    lauben
    0.42
    lopen
    0.41
    homa
    0.41
    __(/*!
    0.40
    ipur
    0.40
    <bos>
    0.40
    ろう
    0.40
    Act Density 0.211%

    No Known Activations