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

    Neuronpedia

    INDEX
    Explanations

    dependence and role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     いう
    0.47
    /-}$
    0.44
    ם
    0.44
    using
    0.43
    и
    0.43
    cena
    0.42
    polygon
    0.40
    Hình
    0.40
    mà
    0.40
     usług
    0.40
    POSITIVE LOGITS
     tremendously
    0.66
     greatly
    0.63
     enormously
    0.60
     immensely
    0.58
     desempeñ
    0.52
     concret
    0.50
     prevenir
    0.49
     adversely
    0.49
     trastornos
    0.48
     controlling
    0.47
    Act Density 0.700%

    No Known Activations