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

    Neuronpedia

    INDEX
    Explanations

    movement and rotation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    сную
    1.03
     prere
    0.96
    hose
    0.96
    री
    0.95
     zah
    0.93
     É
    0.93
    pand
    0.91
     अमृत
    0.90
    Alc
    0.90
    know
    0.90
    POSITIVE LOGITS
     متجه
    1.20
    त्ति
    1.01
     випадку
    0.97
    大規模
    0.96
    超过
    0.95
    টারের
    0.95
    戦
    0.94
     Armenians
    0.94
    ϲ
    0.94
     ولكن
    0.93
    Act Density 0.000%

    No Known Activations