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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    3
    -0.09
    2
    -0.09
    4
    -0.08
    0
    -0.08
    5
    -0.07
    7
    -0.07
    6
    -0.07
     humans
    -0.07
    Consider
    -0.06
    imated
    -0.06
    POSITIVE LOGITS
     thirty
    0.12
     fifteen
    0.12
     twelve
    0.12
     fifty
    0.12
     eighteen
    0.12
     eleven
    0.12
     thirteen
    0.11
     fourteen
    0.11
     sixty
    0.11
     sixteen
    0.10
    Act Density 0.017%

    No Known Activations