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

    Neuronpedia

    INDEX
    Explanations

    loading pretrained models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    inios
    0.48
    ilded
    0.44
    тор
    0.43
    𝖐
    0.39
    єте
    0.39
     luster
    0.39
    ianos
    0.38
    ܤ
    0.38
    ресень
    0.38
    imd
    0.38
    POSITIVE LOGITS
     wiring
    0.44
     Nuggets
    0.41
     used
    0.41
     utilizadas
    0.41
    ی
    0.41
     protest
    0.40
     Proven
    0.40
    ब
    0.40
     parade
    0.40
    pretrained
    0.40
    Act Density 0.000%

    No Known Activations