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

    Neuronpedia

    INDEX
    Explanations

    terms related to explosions and dramatic events

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

    "blow" and its forms

    np_acts-logits-general · gemini-2.0-flash

    blow up or past

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.94
    floxacin
    -0.63
    fficients
    -0.60
    !("{
    -0.59
    creativecommons
    -0.59
    ImageContext
    -0.59
    ^(
    -0.56
    inds
    -0.55
    帖最后由
    -0.54
    ∉
    -0.54
    POSITIVE LOGITS
     blown
    1.31
     blew
    1.20
     blow
    1.14
    blown
    1.13
     Blow
    1.09
    Blow
    1.08
     blowing
    1.05
     blasts
    1.03
     explosions
    1.02
     deton
    1.02
    Act Density 0.219%

    No Known Activations