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

    Neuronpedia

    INDEX
    Explanations

    a company name or news organization followed by a comma

    oai_token-act-pair · gemini-2.0-flash

    comma

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    parsedMessage
    -0.71
    「
    -0.63
    Personensuche
    -0.56
     Offisielt
    -0.56
     كومونز
    -0.56
     protoimpl
    -0.55
     دیکھیے
    -0.54
    ########.
    -0.51
    :");
    -0.50
    Климат
    -0.50
    POSITIVE LOGITS
     etc
    1.10
     among
    0.74
    etc
    0.74
     and
    0.73
    among
    0.59
     Etc
    0.57
     além
    0.56
     amongst
    0.54
     ect
    0.54
    および
    0.52
    Act Density 2.907%

    No Known Activations