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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical activities, particularly those related to movement and exercise

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

    describing actions or movement

    np_acts-logits-general · gemini-2.0-flash

    actions described how

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LEncoder
    -0.60
    xffffffff
    -0.57
    ⎩
    -0.56
     GenerationType
    -0.56
    ="@+
    -0.55
    IBLES
    -0.55
     ')[
    -0.54
    ulties
    -0.54
    reya
    -0.53
    ませんでした
    -0.53
    POSITIVE LOGITS
     freely
    0.63
     furiously
    0.62
     hard
    0.54
     away
    0.54
     madly
    0.53
     profondément
    0.53
     Ră
    0.51
     profusely
    0.50
     differently
    0.50
     conseguenza
    0.50
    Act Density 0.348%

    No Known Activations