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

    Neuronpedia

    INDEX
    Explanations

    mod followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    annie
    0.49
    ADE
    0.46
    ALLOW
    0.44
     Allow
    0.42
    Bin
    0.42
     Break
    0.41
     Managing
    0.40
     Explain
    0.40
    ütfen
    0.40
     जम
    0.40
    POSITIVE LOGITS
     mod
    0.98
    Mod
    0.96
     Mod
    0.96
     MOD
    0.89
    mod
    0.80
     Modi
    0.76
     modList
    0.76
     मोदी
    0.73
     moder
    0.73
     mods
    0.73
    Act Density 0.017%

    No Known Activations