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

    Neuronpedia

    INDEX
    Explanations

    Final Answer:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    utzerklärung
    1.00
     dizendo
    0.95
     ""),
    0.91
     ني
    0.88
    ✐
    0.86
     statunit
    0.86
    ≜
    0.86
     കഴിയ
    0.85
     pedibusque
    0.85
    UCLEAR
    0.85
    POSITIVE LOGITS
    mach
    0.70
    Rep
    0.70
    Avoid
    0.70
    Oc
    0.67
    Make
    0.67
    Highly
    0.67
    Bre
    0.66
    不利
    0.64
    B
    0.63
     highly
    0.63
    Act Density 0.038%

    No Known Activations