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

    Neuronpedia

    INDEX
    Explanations

    five

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    、私
    -0.07
     altering
    -0.07
    ouis
    -0.07
    ्रदर
    -0.06
    <Menu
    -0.06
     Pvt
    -0.06
     společ
    -0.06
     Из
    -0.06
     benefiting
    -0.06
     infographic
    -0.06
    POSITIVE LOGITS
     Nil
    0.08
    Nil
    0.07
    (ii
    0.07
    _SIG
    0.06
    _sb
    0.06
    _uc
    0.06
     Shotgun
    0.06
    Fit
    0.06
     Massage
    0.06
    串
    0.06
    Act Density 0.000%

    No Known Activations