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

    Neuronpedia

    INDEX
    Explanations

    generate consistent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jednotliv
    0.56
    علان
    0.53
     Zden
    0.48
    phalodes
    0.47
     استعمال
    0.47
    nst
    0.47
     उद्योग
    0.46
     kombin
    0.46
    ંત્રણ
    0.46
     Gazprom
    0.46
    POSITIVE LOGITS
    als
    0.44
    If
    0.40
     synchronization
    0.40
    Fa
    0.40
     compressed
    0.39
    вих
    0.39
    ಷ್ಟು
    0.39
    ව්
    0.39
     compressive
    0.39
     likened
    0.38
    Act Density 0.000%

    No Known Activations