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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lot
    -0.07
     ду
    -0.06
    ूबर
    -0.06
    .Emit
    -0.06
    ]‏
    -0.06
     TMP
    -0.06
    *z
    -0.06
    BST
    -0.06
     zar
    -0.06
    .rb
    -0.06
    POSITIVE LOGITS
     biases
    0.07
    aria
    0.06
     prostituerte
    0.06
    麻
    0.06
     mourning
    0.06
    ्म
    0.06
    eshire
    0.06
    /add
    0.06
    /yyyy
    0.06
    mah
    0.06
    Act Density 0.041%

    No Known Activations