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

    Neuronpedia

    INDEX
    Explanations

    принц-полукровка

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     راجس
    0.51
    ၣ်
    0.51
    စျေး
    0.50
     stratég
    0.50
    ра
    0.48
     pontos
    0.48
    ونت
    0.47
    يروس
    0.47
     kontinuier
    0.46
    ButtonBar
    0.46
    POSITIVE LOGITS
    peut
    0.52
    lers
    0.47
     overhaul
    0.46
     visits
    0.46
     toys
    0.46
     their
    0.46
    ny
    0.45
     Outstanding
    0.44
    corporate
    0.44
    0.43
    Act Density 0.000%

    No Known Activations