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

    Neuronpedia

    INDEX
    Explanations

    discussions centering around theoretical and principled frameworks

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

    in theory or principle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Referências
    -0.41
    azgo
    -0.39
    rungsseite
    -0.39
    ctors
    -0.37
     resourceCulture
    -0.36
     ब्रेकडाउन
    -0.35
    MENAFN
    -0.35
    uação
    -0.35
    RTLU
    -0.35
    Ży
    -0.35
    POSITIVE LOGITS
     theoretically
    1.20
     Theore
    0.98
    theore
    0.89
    Theore
    0.86
     theore
    0.81
     theoretical
    0.81
    理论
    0.79
     Theoretical
    0.76
    theoretical
    0.76
    Theoretical
    0.74
    Act Density 0.070%

    No Known Activations