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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dvěma
    -0.07
     Mong
    -0.07
    .allocate
    -0.07
     Ziel
    -0.06
     GHz
    -0.06
     Jal
    -0.06
    GES
    -0.06
    986
    -0.06
     IAM
    -0.06
    /orders
    -0.06
    POSITIVE LOGITS
     what
    0.16
     What
    0.13
     WHAT
    0.12
    what
    0.12
    What
    0.11
    "What
    0.09
    “What
    0.09
    WHAT
    0.09
    .What
    0.08
    什么
    0.08
    Act Density 0.153%

    No Known Activations