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

    Neuronpedia

    INDEX
    Explanations

    grouping similar items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trouvait
    0.48
     desafios
    0.46
     serem
    0.45
     midline
    0.45
     buildings
    0.45
     trouver
    0.44
     futuristic
    0.44
     cherished
    0.44
     treasured
    0.44
     clotting
    0.43
    POSITIVE LOGITS
    IA
    0.47
    ha
    0.45
    ang
    0.45
     お客様
    0.45
    UAE
    0.44
    India
    0.44
    Soviet
    0.44
    protein
    0.44
    ED
    0.43
    PO
    0.43
    Act Density 0.000%

    No Known Activations