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

    Neuronpedia

    INDEX
    Explanations

    the term "hard" in various contexts

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

    hard followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    PreInfinity
    -0.74
    "}},
    -0.61
     MenuItem
    -0.60
     IFTT
    -0.57
    iibo
    -0.56
    %)$
    -0.55
    viewType
    -0.53
     menuItem
    -0.52
     виправивши
    -0.51
     itemView
    -0.51
    POSITIVE LOGITS
     Hard
    1.95
    Hard
    1.91
     hard
    1.81
    hard
    1.70
     HARD
    1.62
    HARD
    1.60
     Harder
    1.28
     harder
    1.27
     Hardin
    1.27
     Harding
    1.26
    Act Density 0.010%

    No Known Activations