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

    Neuronpedia

    INDEX
    Explanations

    the letter "h" in various contexts

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

    header file import

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xymatrix
    -0.47
    TagNumber
    -0.47
    bindingNavigator
    -0.46
     Meksiku
    -0.46
    Климат
    -0.45
     noqa
    -0.44
    ecap
    -0.43
    だから
    -0.42
     ""],
    -0.42
    %)$
    -0.42
    POSITIVE LOGITS
     étoient
    0.52
     feroit
    0.48
     aislada
    0.47
    日閲覧
    0.47
     avoient
    0.46
    ähteet
    0.45
     auroit
    0.44
     presidencia
    0.42
    ltä
    0.42
    diven
    0.42
    Act Density 0.001%

    No Known Activations