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

    Neuronpedia

    INDEX
    Explanations

    Slavic surnames

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bamboo
    0.69
     Sesam
    0.67
     phthal
    0.66
     Hadoop
    0.63
     parcel
    0.60
    Ground
    0.60
     XM
    0.59
     Hermes
    0.59
     RSS
    0.59
    誕
    0.58
    POSITIVE LOGITS
    enko
    1.59
    ovski
    1.59
    ova
    1.58
    ovsk
    1.57
    ov
    1.56
    ovich
    1.53
    kov
    1.50
    henko
    1.49
    ovsky
    1.48
    iev
    1.48
    Act Density 0.022%

    No Known Activations