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

    Neuronpedia

    INDEX
    Explanations

    square kilometers (sq mi)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     कोतवाली
    1.55
    1.45
    )`
    1.36
    =
    1.35
    )，
    1.33
     électrique
    1.31
     arrêt
    1.27
    )：
    1.26
    きた
    1.23
     excit
    1.23
    POSITIVE LOGITS
    leys
    1.69
    aned
    1.61
    znych
    1.59
    ando
    1.56
    ل
    1.55
    imli
    1.54
    RY
    1.50
    yiz
    1.46
    ependent
    1.45
    actic
    1.45
    Act Density 0.002%

    No Known Activations