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

    Neuronpedia

    INDEX
    Explanations

    references to a specific file path or directory

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

    paths starting with /home/

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doloroso
    -0.36
     fiscales
    -0.35
     educativos
    -0.32
     dramatique
    -0.31
     dolorosa
    -0.31
    hilangan
    -0.31
     didst
    -0.30
     inneces
    -0.30
     australiano
    -0.30
     coleccion
    -0.30
    POSITIVE LOGITS
    home
    1.35
    HOME
    1.30
     home
    1.30
     Home
    1.22
     HOME
    1.21
    Home
    1.19
     홈
    0.92
    homes
    0.91
    ホーム
    0.89
     AssemblyCompany
    0.89
    Act Density 0.005%

    No Known Activations