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

    Neuronpedia

    INDEX
    Explanations

    sometimes luck

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     commensurate
    0.46
     marketplaces
    0.44
     Connelly
    0.43
    është
    0.42
     cosmology
    0.42
    Cartoon
    0.42
    Tunes
    0.41
    ﺑ
    0.41
     caricature
    0.40
     doğum
    0.40
    POSITIVE LOGITS
     anos
    0.52
    ᓛ
    0.50
     alumnos
    0.47
    ros
    0.46
     উক্ত
    0.46
     vissa
    0.45
     años
    0.42
     anni
    0.42
     goles
    0.42
     korte
    0.41
    Act Density 0.029%

    No Known Activations