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

    Neuronpedia

    INDEX
    Explanations

    json-like data structures.

    oai_token-act-pair · gemini-2.0-flash

    colons, quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -0.79
    Portail
    -0.71
     LZ
    -0.66
    فایل‌لار
    -0.63
    IsMutable
    -0.63
     للمعارف
    -0.62
    Geplaatst
    -0.61
    ContentAsync
    -0.60
     Sciento
    -0.60
    GEBURTSDATUM
    -0.59
    POSITIVE LOGITS
    ValueGeneration
    0.52
    ständig
    0.49
     litté
    0.49
    füllen
    0.47
    omitempty
    0.46
    inosi
    0.45
     financières
    0.45
     we
    0.44
    IALS
    0.43
     "",
    0.43
    Act Density 0.795%

    No Known Activations