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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Manit
    -0.08
     findById
    -0.07
    鞫
    -0.07
    /Edit
    -0.07
     dara
    -0.07
     dân
    -0.07
    人
    -0.07
     nevertheless
    -0.07
    .receiver
    -0.07
     Chief
    -0.06
    POSITIVE LOGITS
    時には
    0.07
    ˗
    0.07
    **:
    0.07
    ()=>
    0.07
    رياض
    0.07
    廣告
    0.07
    Blo
    0.06
    五四
    0.06
    );
    0.06
     steril
    0.06
    Act Density 0.015%

    No Known Activations