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

    Neuronpedia

    INDEX
    Explanations

    dates and code terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ectic
    1.23
    ESTAMP
    1.12
     tempi
    1.11
    तुर
    1.05
    สห
    1.00
    opolar
    0.98
     nasty
    0.96
    เจน
    0.95
     manual
    0.94
     বিপর্যয়
    0.93
    POSITIVE LOGITS
    itemView
    1.32
    ні
    1.30
     virtuous
    1.13
     participé
    1.12
    𝘧
    1.05
    ни
    1.05
    شک
    1.05
     conduits
    1.04
    ządz
    1.02
    گوید
    1.01
    Act Density 0.000%

    No Known Activations