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

    Neuronpedia

    INDEX
    Explanations

    pone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Pr
    -0.07
    仰
    -0.06
     drawn
    -0.06
    bc
    -0.06
    rray
    -0.06
    رفت
    -0.06
     Concat
    -0.06
     {:.
    -0.06
    was
    -0.06
     hadn
    -0.06
    POSITIVE LOGITS
    �
    0.07
     begged
    0.06
     Quyết
    0.06
     yüksel
    0.06
     Stoke
    0.06
     volleyball
    0.06
     party
    0.06
     Pablo
    0.06
    plete
    0.06
     martial
    0.06
    Act Density 0.002%

    No Known Activations