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

    Neuronpedia

    INDEX
    Explanations

    two main blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TER
    0.46
    nici
    0.45
    TO
    0.45
    Google
    0.43
    ニコ
    0.43
     keterangan
    0.42
     ricco
    0.42
     ámbito
    0.41
    Twitter
    0.41
     adına
    0.41
    POSITIVE LOGITS
    uras
    0.50
    zeit
    0.50
    ant
    0.46
     పూర్
    0.46
     F
    0.45
    urous
    0.45
    ar
    0.44
     CLA
    0.43
     второй
    0.42
     المعاد
    0.42
    Act Density 0.004%

    No Known Activations