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

    Neuronpedia

    INDEX
    Explanations

    complex and abstract concepts related to growth and development

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

    suffix completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.89
    Personendaten
    -0.88
    GEBURTSDATUM
    -0.88
     kasarigan
    -0.81
    uxxxx
    -0.78
     يتيمه
    -0.76
    Portail
    -0.76
    oredCriteria
    -0.75
     pinulongan
    -0.75
    +#+#
    -0.75
    POSITIVE LOGITS
     bege
    0.35
    僕は
    0.34
    dagangan
    0.33
     jí
    0.33
    或许
    0.32
    proc
    0.32
    僕が
    0.31
     real
    0.30
     po
    0.30
    ini
    0.30
    Act Density 0.480%

    No Known Activations