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

    Neuronpedia

    INDEX
    Explanations

    SAMHSA National Helpline 1-800-662-HELP

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     reduct
    0.77
     anim
    0.75
     Boss
    0.68
     liber
    0.68
    ሠ
    0.66
    اح
    0.66
     BFF
    0.65
     hại
    0.65
    äts
    0.65
    ষণ
    0.65
    POSITIVE LOGITS
    המ
    0.86
    ﻡ
    0.85
    ویز
    0.83
    ޘ
    0.82
     আওতায়
    0.81
    algebras
    0.80
    <unused2064>
    0.80
     शुर
    0.79
    rgb
    0.79
    và
    0.78
    Act Density 0.005%

    No Known Activations