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

    Neuronpedia

    INDEX
    Explanations

    Na⁺, grow, float, Moon, coal, Sword in the Stone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ެއް
    0.59
     repayments
    0.52
    ﻢ
    0.52
    لى
    0.50
    िनय
    0.50
     nível
    0.49
    ⵣ
    0.49
     śmier
    0.49
     શે
    0.49
    पटॉप
    0.48
    POSITIVE LOGITS
    ta
    0.63
    un
    0.51
    ado
    0.51
    į
    0.49
    ized
    0.49
    wei
    0.48
    ：
    0.47
    ika
    0.47
     D
    0.46
    ty
    0.46
    Act Density 0.000%

    No Known Activations