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

    Neuronpedia

    INDEX
    Explanations

    references to modulation and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mod variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     oczy
    -0.40
     Petersburg
    -0.39
    inthe
    -0.38
    here
    -0.38
     rzeczyw
    -0.37
     metais
    -0.37
    PYX
    -0.37
    InThe
    -0.36
    ––––
    -0.36
    These
    -0.35
    POSITIVE LOGITS
     mod
    2.31
     Mod
    2.23
    mod
    2.09
    Mod
    2.05
     MOD
    1.75
    MOD
    1.73
     mods
    1.62
     modding
    1.60
     Mods
    1.55
    bmod
    1.46
    Act Density 0.010%

    No Known Activations