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

    Neuronpedia

    INDEX
    Explanations

    data-driven decisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dropping
    0.41
     psychosis
    0.40
     మారింది
    0.40
     Robo
    0.39
     भिखारी
    0.39
     Photo
    0.38
    盉
    0.38
    陏
    0.38
     lights
    0.38
     হারানোর
    0.38
    POSITIVE LOGITS
    itively
    0.39
    etailed
    0.38
     Zwe
    0.37
     מפ
    0.37
    frog
    0.37
     poked
    0.36
    ativement
    0.36
    дый
    0.35
    yszer
    0.35
    ங்கோ
    0.35
    Act Density 0.000%

    No Known Activations