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

    Neuronpedia

    INDEX
    Explanations

    bypassing conscious thought

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )(-
    0.39
     Ashraf
    0.38
     কমলা
    0.37
    setRoi
    0.37
    ρυθ
    0.37
    Matrices
    0.36
    madı
    0.36
    вым
    0.35
    скими
    0.35
    パー
    0.35
    POSITIVE LOGITS
     nhìn
    0.40
     сейчас
    0.40
    犯
    0.37
    endor
    0.37
    ği
    0.36
     posuere
    0.36
    buffalo
    0.36
     бути
    0.36
    translation
    0.36
     humanitarian
    0.35
    Act Density 0.000%

    No Known Activations