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

    Neuronpedia

    INDEX
    Explanations

    locations and proximity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    everything
    0.43
     இவற்றை
    0.41
     ballerina
    0.40
    any
    0.39
     everything
    0.39
    inguém
    0.39
     abundance
    0.38
    Эти
    0.38
    没有人
    0.38
     member
    0.37
    POSITIVE LOGITS
    Guests
    0.67
     Guests
    0.66
    Nearest
    0.60
     guests
    0.57
     Nearby
    0.55
     najbli
    0.52
     Nearest
    0.52
    closest
    0.51
     Additionally
    0.51
     nearest
    0.50
    Act Density 0.001%

    No Known Activations