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

    Neuronpedia

    INDEX
    Explanations

    kinetic, kinematic, kinesthetic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    1.63
    re
    1.61
    t
    1.57
    in
    1.44
    I
    1.37
    un
    1.36
    n
    1.35
    ung
    1.30
    v
    1.28
    ar
    1.24
    POSITIVE LOGITS
     kin
    1.38
    ;
    1.19
     kinetic
    1.16
     כי
    1.13
     kinet
    1.13
     powied
    1.13
     kinematics
    1.09
     kinematic
    1.07
     kina
    1.07
     fino
    1.05
    Act Density 0.008%

    No Known Activations