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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CUR
    -0.07
     Stuttgart
    -0.07
    nehmer
    -0.07
    Fra
    -0.07
     Dortmund
    -0.06
     bisher
    -0.06
     tyto
    -0.06
     eiusmod
    -0.06
     presumption
    -0.06
     jedem
    -0.06
    POSITIVE LOGITS
     paired
    0.06
     ">↵
    0.06
    ','=',
    0.06
    ."',
    0.06
    %H
    0.06
    祭
    0.06
    였
    0.06
     Head
    0.06
     bloss
    0.06
    __':
↵
    0.06
    Act Density 0.001%

    No Known Activations