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

    Neuronpedia

    INDEX
    Explanations

    commands and packages used in LaTeX typesetting

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

    "\usepackage" LaTeX command

    np_acts-logits-general · gemini-2.0-flash

    iron limitation, we affirm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.74
     &___
    -0.73
    IVEREF
    -0.71
    তথ্যসূত্র
    -0.69
     nakalista
    -0.69
    unknownFields
    -0.67
     vedi
    -0.66
    principalColumn
    -0.66
    IANGLES
    -0.65
    Salta
    -0.65
    POSITIVE LOGITS
    usepackage
    2.08
    ñores
    0.58
     Reinh
    0.55
    λευ
    0.55
     Vex
    0.55
    owanego
    0.54
    ñora
    0.53
    ftagPool
    0.53
     Pyle
    0.52
     Layla
    0.52
    Act Density 0.017%

    No Known Activations