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

    Neuronpedia

    INDEX
    Explanations

    mother figure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     In
    0.50
    顿
    0.48
     Healthcare
    0.48
     невероят
    0.47
     Tax
    0.47
     उन्हें
    0.44
     No
    0.44
    in
    0.43
     Taxes
    0.43
     Boost
    0.43
    POSITIVE LOGITS
     gruppo
    0.52
     orientations
    0.52
     grupp
    0.51
     kome
    0.50
     sasan
    0.47
     bhan
    0.47
    ھ
    0.47
    واحد
    0.46
     selen
    0.46
    堹
    0.46
    Act Density 0.000%

    No Known Activations