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

    Neuronpedia

    INDEX
    Explanations

    expressions of skills and abilities

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

    Ability or potential to do something

    np_acts-logits-general · gemini-2.0-flash

    ability to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Савезне
    -0.61
     reforzar
    -0.55
    tryk
    -0.55
     educativas
    -0.53
     tentativa
    -0.53
     garansi
    -0.52
     forsø
    -0.51
     renfor
    -0.51
     hoping
    -0.49
     confirmado
    -0.49
    POSITIVE LOGITS
     potrafi
    0.71
     ability
    0.68
     handling
    0.64
     handle
    0.61
     Umgang
    0.61
     Fähigkeit
    0.60
    featureID
    0.60
     convincingly
    0.59
     skillfully
    0.59
    handles
    0.59
    Act Density 0.287%

    No Known Activations