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

    Neuronpedia

    INDEX
    Explanations

    same

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drei
    -0.08
    拜
    -0.07
    ắn
    -0.07
     между
    -0.06
     seinem
    -0.06
     trộn
    -0.06
    흥
    -0.06
     슈
    -0.06
     cứ
    -0.06
    ",__
    -0.06
    POSITIVE LOGITS
     same
    0.09
    Same
    0.07
    (Constructor
    0.07
     questioned
    0.07
    Env
    0.07
     palindrome
    0.06
     podob
    0.06
     eyeb
    0.06
     identical
    0.06
     jub
    0.06
    Act Density 0.039%

    No Known Activations