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

    Neuronpedia

    INDEX
    Explanations

    citation end punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     derivs
    0.40
     quench
    0.39
     publiés
    0.39
     gaussian
    0.38
    量を
    0.38
     NSUTF
    0.38
    量の
    0.38
     deformations
    0.38
     ScriptInterface
    0.37
    量的
    0.37
    POSITIVE LOGITS
    ærer
    0.39
    bery
    0.39
    ேட்
    0.39
    mozilla
    0.38
    áte
    0.38
     Molina
    0.38
    commit
    0.38
     среднего
    0.37
    akan
    0.37
     Bartlett
    0.37
    Act Density 0.000%

    No Known Activations