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

    Neuronpedia

    INDEX
    Explanations

    events and changes observed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Fact
    0.43
     abode
    0.40
    onomics
    0.39
     alterar
    0.39
    yland
    0.38
     kunde
    0.38
     modifies
    0.37
     ويمكن
    0.36
    configuring
    0.36
     modifying
    0.35
    POSITIVE LOGITS
     arise
    0.59
    出现
    0.57
     entstehen
    0.57
     появления
    0.55
     появ
    0.52
     surgir
    0.52
     powst
    0.51
     attempts
    0.50
     появля
    0.49
     rise
    0.48
    Act Density 0.003%

    No Known Activations