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

    Neuronpedia

    INDEX
    Explanations

    patterns of numerical and alphabetical strings

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

    numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    VersionUID
    -0.68
    principalColumn
    -0.67
    KommentareTeilen
    -0.66
     CanadaChoose
    -0.61
     defaultstate
    -0.60
    kháu
    -0.58
     propOrder
    -0.58
    MigrationBuilder
    -0.57
    躇
    -0.57
    Chham
    -0.56
    POSITIVE LOGITS
     volks
    0.38
     popolari
    0.37
    atmosphère
    0.35
     rodilla
    0.34
     Estadual
    0.34
     rodillas
    0.33
    vator
    0.33
     Smart
    0.32
     maquiagem
    0.32
     ochi
    0.32
    Act Density 0.042%

    No Known Activations