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

    Neuronpedia

    INDEX
    Explanations

    references and providers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     തുടങ്ങി
    0.40
     currentUser
    0.39
     вый
    0.38
    ifferentiated
    0.38
     timeless
    0.37
     copy
    0.37
     erection
    0.37
     কর্তৃত্ব
    0.37
    文学
    0.36
     populous
    0.36
    POSITIVE LOGITS
     Ref
    0.59
    Ref
    0.58
    refs
    0.57
     Provider
    0.54
    Provider
    0.54
    reference
    0.51
     refs
    0.51
     Reference
    0.50
    ref
    0.50
    provider
    0.49
    Act Density 0.000%

    No Known Activations