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

    Neuronpedia

    INDEX
    Explanations

    Python programming language

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     expense
    0.58
    ത്ത്
    0.56
    လည်း
    0.53
     lain
    0.52
     нажмите
    0.52
    х
    0.52
    然後
    0.52
    шена
    0.52
    ने
    0.52
    िका
    0.49
    POSITIVE LOGITS
    0.64
    StateToProps
    0.64
     conceptions
    0.63
     thaliana
    0.63
    lı
    0.63
     ResultSet
    0.62
     partic
    0.61
    Trich
    0.61
    ΜΑ
    0.59
     trainable
    0.59
    Act Density 1.144%

    No Known Activations