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

    Neuronpedia

    INDEX
    Explanations

    hedging language and discussion of assumptions and risk.

    oai_token-act-pair · gemini-2.0-flash

    concepts related to limits or boundaries

    np_token-act-pair-logits · gpt-4o-mini

    beyond/outside

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ngdoc
    -0.75
    #+#
    -0.70
     actionMode
    -0.67
    Personendaten
    -0.67
     CWE
    -0.66
     eventdata
    -0.60
     SafeMath
    -0.59
     MonoBehaviour
    -0.59
    noinspection
    -0.57
    WSGI
    -0.54
    POSITIVE LOGITS
     beyond
    2.13
    beyond
    1.95
     Beyond
    1.82
    Beyond
    1.73
     BEYOND
    1.68
     outside
    1.54
    Outside
    1.41
     Outside
    1.39
    outside
    1.37
     out
    1.24
    Act Density 2.280%

    No Known Activations