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

    Neuronpedia

    INDEX
    Explanations

    delegates signed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    证
    0.50
    事实
    0.45
    вим
    0.45
    、$
    0.42
    டுதல்
    0.41
    栆
    0.41
    סים
    0.40
    Probit
    0.40
    চিব
    0.40
    бом
    0.40
    POSITIVE LOGITS
    t
    0.51
    GetLength
    0.50
     pledged
    0.48
    iena
    0.47
    oger
    0.47
     panjang
    0.46
     to
    0.45
     podido
    0.45
     necessitated
    0.44
    ronidazole
    0.44
    Act Density 0.001%

    No Known Activations