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

    Neuronpedia

    INDEX
    Explanations

    oc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -eff
    -0.08
    和社会
    -0.07
    .bias
    -0.07
     شب
    -0.07
    Brit
    -0.07
     Blues
    -0.07
     прекрас
    -0.07
     доб
    -0.06
    あたり
    -0.06
    佔
    -0.06
    POSITIVE LOGITS
    изм
    0.08
     pathlib
    0.08
     pathology
    0.08
    äl
    0.07
    iterated
    0.07
     ValueError
    0.07
    iban
    0.07
    节约
    0.07
    presentation
    0.07
    ():↵↵
    0.07
    Act Density 0.000%

    No Known Activations