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

    Neuronpedia

    INDEX
    Explanations

    software and pain

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Well
    0.50
    Ş
    0.50
    ｲ
    0.50
    𝗖
    0.49
    ೂರ್ವ
    0.49
    䐍
    0.48
    зной
    0.46
    Υ
    0.46
    墓
    0.46
    ⦖
    0.46
    POSITIVE LOGITS
    ille
    0.58
     tau
    0.56
     संभाल
    0.52
     chanc
    0.52
     kom
    0.51
    ekten
    0.50
    ien
    0.50
    ända
    0.49
    िस्ट
    0.49
    യായി
    0.49
    Act Density 0.000%

    No Known Activations