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

    Neuronpedia

    INDEX
    Explanations

    instructions or prompts related to checking and updating information or content

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

    check, visit, back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    menti
    -0.48
    ❹
    -0.46
    ezers
    -0.45
    chet
    -0.43
    krom
    -0.42
    urther
    -0.42
    /**
    -0.42
    に着
    -0.42
    mosis
    -0.41
     Diver
    -0.41
    POSITIVE LOGITS
     kasarigan
    0.53
     мәкал
    0.46
     nahilalakip
    0.45
    Tazama
    0.45
     kaarangay
    0.43
    Spoljašnje
    0.41
     titulares
    0.39
    pushFollow
    0.38
     oprot
    0.38
    #+#
    0.37
    Act Density 0.004%

    No Known Activations