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

    Neuronpedia

    INDEX
    Explanations

    hip

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     رأ
    -0.07
     тщ
    -0.07
     luz
    -0.06
    _report
    -0.06
    (D
    -0.06
    샤
    -0.06
     přen
    -0.06
    라고
    -0.06
     средств
    -0.06
       ↵    ↵
    -0.06
    POSITIVE LOGITS
     Hip
    0.15
     hip
    0.14
    Hip
    0.10
    hip
    0.09
     HIP
    0.09
    hipster
    0.09
    HIP
    0.08
    ship
    0.08
    親
    0.07
    hips
    0.06
    Act Density 0.003%

    No Known Activations