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

    Neuronpedia

    INDEX
    Explanations

    pop singers and actresses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     zlat
    0.71
    ๛
    0.71
     Fragen
    0.70
    LookAndFeelInfo
    0.69
    ित
    0.67
     juli
    0.66
     LMF
    0.66
    lj
    0.66
     SINGH
    0.66
    )%
    0.64
    POSITIVE LOGITS
    க்கும்
    0.75
    ’
    0.64
    yor
    0.61
    hazardous
    0.60
    uée
    0.59
     instructional
    0.57
    pady
    0.57
    ן
    0.57
    ერ
    0.56
    uras
    0.56
    Act Density 0.001%

    No Known Activations