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

    Neuronpedia

    INDEX
    Explanations

    local sports and recovered materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pierre
    0.44
    オーバー
    0.40
    ่อม
    0.38
    over
    0.38
    Alberto
    0.38
    ше
    0.38
     livre
    0.37
     pave
    0.37
     Darren
    0.37
     Livre
    0.37
    POSITIVE LOGITS
     Bigger
    0.41
     شیطان
    0.40
    bigger
    0.39
    ช่วย
    0.39
    walled
    0.39
    ogloss
    0.38
     bigger
    0.38
     SDLK
    0.38
     Commitment
    0.38
    زد
    0.37
    Act Density 0.004%

    No Known Activations