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

    Neuronpedia

    INDEX
    Explanations

    expressing itself

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Condition
    0.51
     учеб
    0.50
    Any
    0.50
    нным
    0.49
    нению
    0.47
    r
    0.47
     детям
    0.47
    EN
    0.46
    Equals
    0.46
    НЕ
    0.46
    POSITIVE LOGITS
    oha
    0.47
     Mehr
    0.45
    aquin
    0.45
    嗜
    0.44
     gamut
    0.44
    पूर्ति
    0.43
     Villain
    0.43
     Talent
    0.42
    outs
    0.42
    éta
    0.42
    Act Density 0.001%

    No Known Activations