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

    Neuronpedia

    INDEX
    Explanations

    nuanced expressions related to visual effects and their impact on perception

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

    distorted mind views

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     autorytatywna
    -0.68
     مرئيه
    -0.63
     intStringLen
    -0.61
     $_(
    -0.59
    GIVEREF
    -0.58
     <<<<<<<<<<<<<<
    -0.58
     NSCoder
    -0.57
    -0.57
     
    -0.56
     >=",
    -0.55
    POSITIVE LOGITS
     distorted
    0.39
     distortions
    0.36
     hallucin
    0.36
     screens
    0.36
     screen
    0.35
     halluc
    0.35
     distortion
    0.35
    tional
    0.34
     view
    0.33
     u
    0.33
    Act Density 0.058%

    No Known Activations