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

    Neuronpedia

    INDEX
    Explanations

    start

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mitar
    -0.06
     punishable
    -0.06
    isValid
    -0.06
    .model
    -0.06
    iful
    -0.06
     English
    -0.06
     fork
    -0.06
    ughters
    -0.06
    ской
    -0.06
     пост
    -0.06
    POSITIVE LOGITS
     проведення
    0.07
    ():↵
    0.07
     espan
    0.07
     jewellery
    0.06
    材料
    0.06
     useStyles
    0.06
    ีฟ
    0.06
     Washer
    0.06
     způsob
    0.06
    RouterModule
    0.06
    Act Density 0.016%

    No Known Activations