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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -errors
    -0.07
     Erect
    -0.07
     Мак
    -0.07
    ?>">↵
    -0.07
     expands
    -0.07
    แอ
    -0.07
    higher
    -0.07
    ᕋ
    -0.07
    .dll
    -0.07
     Tenant
    -0.07
    POSITIVE LOGITS
    面条
    0.08
    裹
    0.07
     воп
    0.07
    問
    0.07
    ransition
    0.07
    OME
    0.07
    Yep
    0.07
     ít
    0.06
    ступ
    0.06
     questo
    0.06
    Act Density 0.051%

    No Known Activations