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

    Neuronpedia

    INDEX
    Explanations

    contact, name, or email

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    لمات
    0.49
    WMat
    0.47
    ސް
    0.47
    uliers
    0.47
     WHIT
    0.47
     प्रेर
    0.46
     सीएस
    0.45
    Σ
    0.45
    APAN
    0.45
    С
    0.45
    POSITIVE LOGITS
     natural
    0.54
    natural
    0.53
     her
    0.45
     chur
    0.45
     ra
    0.45
     nom
    0.44
     hut
    0.43
    dad
    0.42
     shrimp
    0.41
     aa
    0.41
    Act Density 0.000%

    No Known Activations