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

    Neuronpedia

    INDEX
    Explanations

    shapes and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sang
    0.40
     sang
    0.40
     fundador
    0.39
    isional
    0.38
     যেটা
    0.38
     วัน
    0.38
    uito
    0.37
     gew
    0.37
    анд
    0.37
     गायिका
    0.37
    POSITIVE LOGITS
     CPU
    0.42
     Wedge
    0.40
     Spotlight
    0.39
    比特
    0.38
    中毒
    0.38
     wedges
    0.38
     IoT
    0.37
     CPUs
    0.37
    Lett
    0.36
     retail
    0.36
    Act Density 0.000%

    No Known Activations