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

    Neuronpedia

    INDEX
    Explanations

    error messages and display

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     usable
    0.92
     adjustable
    0.86
    亍
    0.84
     exponential
    0.83
    犧
    0.83
     logarithm
    0.79
     Jackie
    0.79
     absc
    0.78
     ettevõ
    0.78
     graphing
    0.77
    POSITIVE LOGITS
    AddModelError
    1.01
     ایر
    0.88
     erreurs
    0.84
    Errors
    0.82
    ungg
    0.82
    messages
    0.81
     SES
    0.81
    inati
    0.77
    SES
    0.76
     kesalahan
    0.76
    Act Density 0.106%

    No Known Activations