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

    Neuronpedia

    INDEX
    Explanations

    listing items with asterisks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sensibilité
    0.47
     analisa
    0.47
    cmb
    0.46
    𝗇
    0.46
    editors
    0.46
    顐
    0.46
    critic
    0.46
    illiant
    0.45
    pseudo
    0.45
     अटेम्प्ट
    0.44
    POSITIVE LOGITS
    _
    0.49
     ssh
    0.47
     router
    0.45
     wooden
    0.44
     schn
    0.44
     бір
    0.44
    臼
    0.44
     服务器
    0.43
    Out
    0.43
     About
    0.42
    Act Density 0.111%

    No Known Activations