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

    Neuronpedia

    INDEX
    Explanations

    structural elements in formal publication references

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

    citations and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.75
     nahilalakip
    -0.74
    utilisons
    -0.70
    ValueStyle
    -0.69
    AndEndTag
    -0.65
     faſt
    -0.64
    ########.
    -0.64
     raiſ
    -0.61
     transfieras
    -0.60
    (!__
    -0.60
    POSITIVE LOGITS
     panel
    0.35
     presentation
    0.33
     oblique
    0.32
     pomeriggio
    0.31
     presenters
    0.31
     presentaciones
    0.31
     πάν
    0.30
    MockBean
    0.30
     obliquely
    0.30
     moderator
    0.30
    Act Density 0.026%

    No Known Activations