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

    Neuronpedia

    INDEX
    Explanations

    analyzing and suggesting actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     змі
    0.50
    ות
    0.46
     юриди
    0.46
     மனு
    0.45
    ഷ്യ
    0.44
    InData
    0.44
    несен
    0.43
    га
    0.43
     Pooling
    0.43
     Segurança
    0.42
    POSITIVE LOGITS
     diaphragm
    0.52
    m
    0.50
    vand
    0.50
     lup
    0.47
     interesar
    0.47
    SWE
    0.47
    div
    0.46
     find
    0.46
     लेट
    0.45
    illa
    0.45
    Act Density 0.000%

    No Known Activations