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

    Neuronpedia

    INDEX
    Explanations

    various numeric values or measurements presented in a structured format

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

    percentages and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iſen
    -0.78
    ſcher
    -0.75
     ſei
    -0.68
    ſchaft
    -0.67
    ſchen
    -0.66
     ſche
    -0.65
     ddelwed
    -0.65
    mpagne
    -0.65
    brakk
    -0.63
    niſſe
    -0.63
    POSITIVE LOGITS
    intios
    0.40
    Agree
    0.40
    ngdoc
    0.38
    subpackage
    0.35
    Councillor
    0.34
    .
    0.34
     astore
    0.33
     Polish
    0.33
    $-.
    0.32
     Prozent
    0.32
    Act Density 0.291%

    No Known Activations