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

    Neuronpedia

    INDEX
    Explanations

    words relating to code and project development.

    oai_token-act-pair · gemini-2.0-flash

    work

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    __(/*!
    -0.77
     AssemblyCompany
    -0.67
    日在
    -0.52
    áře
    -0.51
    atalos
    -0.49
    urança
    -0.49
     статистики
    -0.49
     kerül
    -0.48
     shroud
    -0.47
    Sass
    -0.47
    POSITIVE LOGITS
     properly
    0.88
     well
    0.83
     correctly
    0.82
     correctement
    0.72
     Properly
    0.69
     better
    0.67
     excellently
    0.66
     poorly
    0.65
     optimally
    0.65
     convenable
    0.65
    Act Density 1.007%

    No Known Activations