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

    Neuronpedia

    INDEX
    Explanations

    negative commentary on societal issues and injustices

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

    . any

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.65
    MarshalTo
    -0.58
    BufferException
    -0.56
    aarrggbb
    -0.55
    numerical
    -0.55
     الحره
    -0.54
    EndContext
    -0.53
     queſto
    -0.52
    AxisAlignment
    -0.52
    ſammen
    -0.52
    POSITIVE LOGITS
    Kjelder
    0.39
     Again
    0.38
    تقاوى
    0.37
    Again
    0.37
    日閲覧
    0.37
    Conf
    0.36
    +:+
    0.34
    Sch
    0.33
    #+#
    0.32
    pok
    0.31
    Act Density 0.013%

    No Known Activations