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

    Neuronpedia

    INDEX
    Explanations

    CSS declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    т
    1.37
    ת
    1.26
    िक्स
    1.04
    ен
    1.03
    תר
    1.02
    लम
    1.00
    ഷ്യ
    0.99
     është
    0.98
    ০
    0.98
     è
    0.97
    POSITIVE LOGITS
     cocoon
    1.49
    Cantidad
    1.36
    toned
    1.28
     strobe
    1.23
     shampoo
    1.21
    haha
    1.19
     Utama
    1.18
     haze
    1.18
     heterogeneity
    1.18
    Classpath
    1.15
    Act Density 0.001%

    No Known Activations