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

    Neuronpedia

    INDEX
    Explanations

    assignments, reviews, theorems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ართ
    -0.09
     മന
    -0.09
    ാറ
    -0.08
     തെള
    -0.08
     konpr
    -0.08
     tires
    -0.08
     suelen
    -0.08
    特码
    -0.08
     皇冠
    -0.07
    )));
    -0.07
    POSITIVE LOGITS
     midpoint
    0.09
     средней
    0.08
    mid
    0.07
     exhort
    0.07
     Statistic
    0.07
     marching
    0.07
    arries
    0.07
     contag
    0.07
    عديل
    0.07
     matang
    0.07
    Act Density 0.001%

    No Known Activations