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

    Neuronpedia

    INDEX
    Explanations

    proving others wrong

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    кологи
    0.38
     कुंडली
    0.37
    ασίας
    0.37
    హిత
    0.36
     Perpet
    0.35
     செய்வத
    0.35
     analyzing
    0.35
     விர
    0.35
    condensation
    0.35
    Analyzing
    0.35
    POSITIVE LOGITS
     proved
    1.53
     prove
    1.49
     proves
    1.49
     proving
    1.33
    proved
    1.31
    prove
    1.29
    证明
    1.27
     Prove
    1.24
    Prove
    1.23
    證明
    1.21
    Act Density 0.007%

    No Known Activations