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

    Neuronpedia

    INDEX
    Explanations

    computational physics and programming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IDs
    0.40
    ifier
    0.38
     রহ
    0.38
     ID
    0.37
     নিয়মিত
    0.37
     обознача
    0.37
    cls
    0.36
    審
    0.36
     decedent
    0.36
     ম
    0.34
    POSITIVE LOGITS
     smog
    0.43
     terrib
    0.43
    meny
    0.43
    pollution
    0.42
     modernas
    0.42
    FAIL
    0.42
     miserably
    0.41
     personnelles
    0.40
     dont
    0.40
     pollution
    0.39
    Act Density 0.000%

    No Known Activations