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

    Neuronpedia

    INDEX
    Explanations

    terms related to primitive values and their characteristics in programming or data structures

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

    Text with bracketed letters

    np_acts-logits-general · gemini-2.0-flash

    approvals, variants, activation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <()>
    -0.49
    siers
    -0.47
    contentLoaded
    -0.47
    dike
    -0.45
    gettes
    -0.44
     <<<<<<<<<<<<<<
    -0.42
    sier
    -0.41
    coroutines
    -0.41
    SIC
    -0.41
    KommentareTeilen
    -0.40
    POSITIVE LOGITS
    v
    0.92
    ########.
    0.64
    vgl
    0.59
    𝒗
    0.58
    vP
    0.56
    vable
    0.56
    vı
    0.55
    ᴠ
    0.55
    vily
    0.54
    vary
    0.54
    Act Density 0.466%

    No Known Activations