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

    Neuronpedia

    INDEX
    Explanations

    ID

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     müdür
    -0.06
     цю
    -0.06
     Md
    -0.06
     wreckage
    -0.06
     Dimensions
    -0.06
     stabilize
    -0.06
    Wis
    -0.06
     jede
    -0.06
     liter
    -0.06
    ويس
    -0.06
    POSITIVE LOGITS
    506
    0.07
    ancias
    0.07
     BBB
    0.07
    ++;
↵
↵
    0.07
    Reviewer
    0.07
    adf
    0.07
    itious
    0.06
     keyst
    0.06
    assessment
    0.06
    Нас
    0.06
    Act Density 0.000%

    No Known Activations