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

    Neuronpedia

    INDEX
    Explanations

    descriptors and characteristics of glowing or colored objects

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

    glowing, colored, pale, black

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inSlope
    -0.45
     autorytatywna
    -0.44
    SharedCtor
    -0.43
     EconPapers
    -0.42
    Tembelea
    -0.41
    ParallelGroup
    -0.41
    -0.41
    kháu
    -0.40
    DockStyle
    -0.40
    Vidite
    -0.39
    POSITIVE LOGITS
    indic
    0.44
    ngOn
    0.43
    indicate
    0.40
    onChangeText
    0.38
    makeText
    0.38
     terlihat
    0.38
    andExpect
    0.38
     seen
    0.38
     indicating
    0.37
     hint
    0.36
    Act Density 0.211%

    No Known Activations