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

    Neuronpedia

    INDEX
    Explanations

    coordinates and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nop
    0.43
    ressed
    0.39
     loved
    0.39
     dialing
    0.39
     sides
    0.38
    oron
    0.38
     posto
    0.37
     cordial
    0.37
     disamb
    0.36
    Loved
    0.36
    POSITIVE LOGITS
    하려면
    0.47
    cimientos
    0.41
     Jurisdiction
    0.41
     осуществляется
    0.40
    判断
    0.39
     न्यायाधीश
    0.38
     строй
    0.38
     বিচার
    0.37
     liderazgo
    0.37
     Öffentlichkeit
    0.37
    Act Density 0.000%

    No Known Activations