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

    Neuronpedia

    INDEX
    Explanations

    generate text or copy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ruining
    0.40
    慳
    0.39
     xb
    0.38
     causando
    0.38
    🧊
    0.38
     spoil
    0.38
     authorise
    0.38
     ruined
    0.38
     MERCHANTABILITY
    0.37
     collect
    0.37
    POSITIVE LOGITS
    avor
    0.43
    地震
    0.41
    handmade
    0.40
    ripción
    0.40
    ному
    0.39
    regional
    0.38
     front
    0.38
    computers
    0.38
    terrorism
    0.38
    hare
    0.38
    Act Density 0.000%

    No Known Activations