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

    Neuronpedia

    INDEX
    Explanations

    heart

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    56
    -0.07
    ائی
    -0.06
    28
    -0.06
    si
    -0.06
    ício
    -0.06
     travellers
    -0.06
    Ni
    -0.06
    취
    -0.06
     cash
    -0.06
    uger
    -0.06
    POSITIVE LOGITS
     Heart
    0.11
     heart
    0.10
     серд
    0.08
    Heart
    0.08
    .hamcrest
    0.07
    .openConnection
    0.07
    %X
    0.07
     gist
    0.07
     heartbreaking
    0.07
    turn
    0.07
    Act Density 0.007%

    No Known Activations