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

    Neuronpedia

    INDEX
    Explanations

    java util.io.net.lang.security

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     acabado
    0.82
     chapitre
    0.80
    리는
    0.79
     atractivo
    0.79
     variado
    0.79
     at
    0.76
    য়াছে
    0.76
     complicado
    0.76
     advogado
    0.76
     aquest
    0.73
    POSITIVE LOGITS
    ba
    0.97
    V
    0.97
    un
    0.89
     I
    0.88
    س
    0.88
    м
    0.87
    K
    0.86
    W
    0.86
    I
    0.81
    с
    0.81
    Act Density 0.006%

    No Known Activations