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

    Neuronpedia

    INDEX
    Explanations

    numeric values and identifiers related to datasets or entries

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

    URLs and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ſicht
    -0.81
    [@BOS@]
    -0.81
    <pad>
    -0.81
    <unused3>
    -0.81
    ſſung
    -0.81
    <unused21>
    -0.81
    <unused74>
    -0.81
    <unused23>
    -0.81
    <unused8>
    -0.81
    <unused17>
    -0.81
    POSITIVE LOGITS
     dilan
    0.32
     brisa
    0.31
     présentés
    0.30
     debut
    0.29
    RegistryLite
    0.28
     interiores
    0.28
    กุ
    0.27
     začet
    0.27
    zések
    0.27
     Schriften
    0.27
    Act Density 0.001%

    No Known Activations