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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Adapter
    -0.07
     rotation
    -0.06
    .filter
    -0.06
    (frame
    -0.06
    tet
    -0.06
     Sergeant
    -0.06
    PX
    -0.06
     orgán
    -0.06
     calloc
    -0.06
     backtrack
    -0.06
    POSITIVE LOGITS
    SN
    0.07
     brilliant
    0.06
    ustralia
    0.06
     ΔΗΜ
    0.06
     przez
    0.06
    젝트
    0.06
    ...\
    0.06
    呢
    0.06
     Banc
    0.06
    ิทธ
    0.06
    Act Density 0.016%

    No Known Activations