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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate legal reasoning or considerations

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

    finds that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IsContent
    -0.49
     åt
    -0.45
     kohdetta
    -0.43
     gela
    -0.43
     Biôgrafia
    -0.41
    balleur
    -0.41
    хьтан
    -0.39
    ContentAsync
    -0.38
     ModelRenderer
    -0.38
     doPost
    -0.38
    POSITIVE LOGITS
    WHEREAS
    1.10
     WHEREAS
    0.60
    dafx
    0.47
     AssemblyCulture
    0.46
     nepiecieš
    0.46
     endwhile
    0.45
     CommonModule
    0.44
    """.
    0.44
    DllImport
    0.44
    didSet
    0.42
    Act Density 0.019%

    No Known Activations