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

    Neuronpedia

    INDEX
    Explanations

    frequency, occurrence counts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     arbres
    0.64
    diamonds
    0.63
     homens
    0.58
    χής
    0.56
     cortos
    0.55
     triangles
    0.55
     direita
    0.54
     aunts
    0.54
     Conseils
    0.54
     carros
    0.53
    POSITIVE LOGITS
    ný
    0.57
     במהלך
    0.56
    ใน
    0.53
    ться
    0.52
    ৭০
    0.51
    ৯
    0.51
    枉
    0.50
    panda
    0.49
    ครั้ง
    0.48
     अगेन
    0.48
    Act Density 0.022%

    No Known Activations