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

    Neuronpedia

    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     testData
    -0.07
    /we
    -0.07
     чуж
    -0.06
     stories
    -0.06
     Below
    -0.06
     امید
    -0.06
    fiber
    -0.06
    edException
    -0.06
     deney
    -0.06
    077
    -0.06
    POSITIVE LOGITS
    acia
    0.06
     حداقل
    0.06
    .fontSize
    0.06
    adecimal
    0.06
    amiento
    0.06
    ском
    0.06
    .return
    0.06
     altered
    0.06
     }*/↵
    0.05
     chauff
    0.05
    Act Density 0.030%

    No Known Activations