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

    Neuronpedia

    INDEX
    Explanations

    foreign language words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ron
    0.45
    น้อง
    0.45
    Mark
    0.43
     revoked
    0.42
    One
    0.42
    KHTML
    0.42
    わ
    0.42
    정
    0.41
    the
    0.40
    verified
    0.40
    POSITIVE LOGITS
     sufr
    0.50
     Policies
    0.49
     ModInt
    0.49
     déficit
    0.48
     enseñanzas
    0.48
     ideales
    0.47
     policies
    0.47
    efeuille
    0.46
     fé
    0.46
     reformas
    0.46
    Act Density 0.007%

    No Known Activations