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

    Neuronpedia

    INDEX
    Explanations

    actions related to data processing and manipulation

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

    performing actions or processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.71
    HostException
    -0.59
    ⪜
    -0.56
    rawDesc
    -0.56
    TagMode
    -0.56
    Vidite
    -0.56
    tvguidetime
    -0.54
    featureID
    -0.54
    OGND
    -0.54
     للمعارف
    -0.54
    POSITIVE LOGITS
    }))
    0.47
     the
    0.40
    }")]
    0.39
    กัน
    0.39
    ]")]
    0.39
     this
    0.37
     to
    0.37
     between
    0.37
    })));
    0.36
     against
    0.35
    Act Density 0.104%

    No Known Activations