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

    Neuronpedia

    INDEX
    Explanations

    phrases related to effort and complexity in tasks

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

    difficulties, negations, and challenges

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     s
    -0.31
    ild
    -0.31
    si
    -0.30
    izin
    -0.30
     اج
    -0.29
    field
    -0.29
    ho
    -0.28
     الس
    -0.28
    ped
    -0.27
    rob
    -0.27
    POSITIVE LOGITS
     indisponible
    0.68
    UnusedPrivate
    0.66
     MutableLiveData
    0.65
    RUnlock
    0.64
     HasFactory
    0.63
     erſten
    0.62
    <unused41>
    0.61
     queſta
    0.61
    <pad>
    0.61
    [@BOS@]
    0.60
    Act Density 0.143%

    No Known Activations