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

    Neuronpedia

    INDEX
    Explanations

    terms associated with cowardice and weakness

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

    cowardice, timidity, fear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     surla
    -0.59
    IntoConstraints
    -0.58
     intStringLen
    -0.54
    ModelAdmin
    -0.54
    ✨:
    -0.53
    FromNib
    -0.50
    MockMvc
    -0.50
     Exacts
    -0.49
     Paglinawan
    -0.48
    Życiorys
    -0.47
    POSITIVE LOGITS
     cowardly
    0.84
     cowardice
    0.73
     coward
    0.70
     cowards
    0.60
     weak
    0.52
     Coward
    0.51
     wim
    0.50
     timid
    0.48
     weakness
    0.44
    懦
    0.43
    Act Density 0.027%

    No Known Activations