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

    Neuronpedia

    INDEX
    Explanations

    After Effects variety space size

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atlet
    0.53
     utilise
    0.51
    з
    0.51
     utilis
    0.48
     adaptés
    0.47
     attaques
    0.47
     Turkmenistan
    0.46
     avert
    0.46
     paralelas
    0.46
     acciaio
    0.46
    POSITIVE LOGITS
     සැ
    0.47
     شب
    0.46
    UM
    0.46
    Ợ
    0.45
    Solve
    0.44
    نت
    0.43
     더욱
    0.43
    inn
    0.42
    Uniform
    0.42
    neet
    0.42
    Act Density 0.001%

    No Known Activations