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

    Neuronpedia

    INDEX
    Explanations

    stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    중
    -0.07
     tan
    -0.07
     accumulating
    -0.06
     tercer
    -0.06
     над
    -0.06
     �
    -0.06
    Пос
    -0.06
     udrž
    -0.06
    Survey
    -0.06
    merchant
    -0.06
    POSITIVE LOGITS
    .Info
    0.07
    Denver
    0.06
    ipeg
    0.06
     flor
    0.06
    HELP
    0.06
    Administr
    0.06
    =Math
    0.06
    LLL
    0.06
     REVIEW
    0.06
    .kind
    0.06
    Act Density 0.039%

    No Known Activations