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

    Neuronpedia

    INDEX
    Explanations

    code/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dining
    -0.06
     Hou
    -0.06
     soc
    -0.06
    ."↵
    -0.06
     org
    -0.06
     namespaces
    -0.06
    -self
    -0.06
     je
    -0.06
     Die
    -0.06
    Bits
    -0.06
    POSITIVE LOGITS
    comments
    0.07
    �
    0.06
    alah
    0.06
    बर
    0.06
     Performs
    0.06
     protested
    0.06
    =~
    0.06
     Emotional
    0.06
    indicator
    0.06
     Feel
    0.06
    Act Density 0.006%

    No Known Activations