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

    Neuronpedia

    INDEX
    Explanations

    coaching, peaks, technical sections, dilute electrolytes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    占比
    0.48
    ڌ
    0.48
    мпа
    0.46
    amplitude
    0.46
    ísmo
    0.45
    linewidth
    0.44
    ónica
    0.44
    posición
    0.44
    evident
    0.44
    slideTo
    0.44
    POSITIVE LOGITS
     every
    0.51
     Glycer
    0.51
     each
    0.50
     Dere
    0.48
     Losing
    0.48
     ourselves
    0.48
     a
    0.48
     Consc
    0.47
     Grief
    0.46
     everything
    0.46
    Act Density 0.004%

    No Known Activations