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

    Neuronpedia

    INDEX
    Explanations

    male relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (us
    -0.09
     Europa
    -0.09
    اضيع
    -0.08
    يسة
    -0.08
     Utah
    -0.08
     الهيئة
    -0.08
     снег
    -0.08
     கலந்து
    -0.08
     التابعة
    -0.08
     europea
    -0.08
    POSITIVE LOGITS
    ivere
    0.08
    ificio
    0.08
     nargs
    0.08
     לאורך
    0.08
    eway
    0.07
     kannst
    0.07
     maximise
    0.07
    *n
    0.07
    cada
    0.07
    *h
    0.07
    Act Density 0.117%

    No Known Activations