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

    Neuronpedia

    INDEX
    Explanations

    terms related to the concept of 'ruin'

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

    ruining things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     QtCore
    -0.61
     persoane
    -0.60
    OGND
    -0.60
    ImageContext
    -0.60
    usercontent
    -0.57
     faptul
    -0.56
     către
    -0.54
    personen
    -0.53
    ($__
    -0.52
    twimg
    -0.51
    POSITIVE LOGITS
     ruining
    0.84
     ruined
    0.84
     ruin
    0.83
     spoil
    0.66
     ruins
    0.63
     spoiled
    0.62
     Ruin
    0.61
     ruine
    0.60
     spoiling
    0.58
     arru
    0.57
    Act Density 0.007%

    No Known Activations