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

    Neuronpedia

    INDEX
    Explanations

    travel blogger

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ின்
    0.51
    comand
    0.48
    ені
    0.47
    ाइ
    0.47
    ಳ್
    0.47
    adjoint
    0.45
    galactos
    0.45
    िप
    0.45
    ichung
    0.44
     simpt
    0.44
    POSITIVE LOGITS
    果然
    0.41
     Canal
    0.40
     Riviera
    0.40
    有两种
    0.39
     guten
    0.38
     Davy
    0.37
     Crochet
    0.37
     исте
    0.37
     Rotterdam
    0.37
    t
    0.37
    Act Density 0.002%

    No Known Activations