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

    Neuronpedia

    INDEX
    Explanations

    terms related to validation or verification processes

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

    <start_of_turn> user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    무
    -0.30
    Encyklopedia
    -0.27
     Jensen
    -0.26
    Quellen
    -0.25
     Haupt
    -0.24
     Heimat
    -0.24
    gantung
    -0.24
    ULD
    -0.24
    pf
    -0.24
     Röntgen
    -0.24
    POSITIVE LOGITS
    0.85
    Clik
    0.85
    KommentareTeilen
    0.75
    хьтан
    0.74
    <unused8>
    0.74
    <unused68>
    0.73
    [@BOS@]
    0.73
    <unused41>
    0.73
    <pad>
    0.73
    <unused14>
    0.73
    Act Density 0.000%

    No Known Activations