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

    Neuronpedia

    INDEX
    Explanations

    对

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     χρό
    -0.07
    YEAR
    -0.07
    �
    -0.06
    (\$
    -0.06
     �
    -0.06
    งเศ
    -0.06
     الل
    -0.06
     Hindi
    -0.06
     الذه
    -0.06
    aska
    -0.06
    POSITIVE LOGITS
    对
    0.09
     对
    0.09
     *)
    0.08
     DialogInterface
    0.07
    एम
    0.07
    ®
    0.07
     boyfriend
    0.06
    .omg
    0.06
     puppet
    0.06
     أيض
    0.06
    Act Density 0.004%

    No Known Activations