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

    Neuronpedia

    INDEX
    Explanations

    cockroach and its variants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    .
    0.63
    ン
    0.62
    つの
    0.60
     persec
    0.60
     ख्याल
    0.59
    ન
    0.57
    ב
    0.57
    سی
    0.57
     yoki
    0.57
    OR
    0.56
    POSITIVE LOGITS
    ί
    0.51
    anı
    0.50
    htb
    0.50
    ﻪ
    0.50
    lado
    0.49
    onds
    0.49
     titulares
    0.49
    end
    0.49
    罗马
    0.49
    kende
    0.49
    Act Density 0.001%

    No Known Activations