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

    Neuronpedia

    INDEX
    Explanations

    its

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     remain
    -0.06
    .tail
    -0.06
    .',
↵
    -0.06
    segue
    -0.06
     Hat
    -0.06
     Initialized
    -0.06
     legacy
    -0.06
     روابط
    -0.06
    never
    -0.06
     primarily
    -0.06
    POSITIVE LOGITS
     zápas
    0.07
     Newtown
    0.07
    橋
    0.07
    @m
    0.07
     是否
    0.07
     opener
    0.06
    inosaur
    0.06
    مارات
    0.06
    田
    0.06
    إن
    0.06
    Act Density 0.000%

    No Known Activations