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

    Neuronpedia

    INDEX
    Explanations

    todos los

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ilidade
    0.68
    óst
    0.55
    Ihr
    0.54
     konnte
    0.50
    like
    0.49
    }}=\
    0.49
     حالة
    0.49
    0.48
     könnte
    0.46
    uada
    0.46
    POSITIVE LOGITS
     Poly
    0.52
     cobalt
    0.52
     blacksmith
    0.51
     Physics
    0.50
     Delft
    0.49
     Cobalt
    0.49
     Glen
    0.48
     Katie
    0.48
     Node
    0.47
     Copper
    0.47
    Act Density 0.000%

    No Known Activations