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

    Neuronpedia

    INDEX
    Explanations

    Code, file paths

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rott
    -0.09
     interpersonal
    -0.09
     city
    -0.09
     SWOT
    -0.08
    .Person
    -0.08
     offent
    -0.08
     意
    -0.08
     शहर
    -0.08
     город
    -0.08
     organizational
    -0.08
    POSITIVE LOGITS
    Native
    0.11
     Native
    0.09
     libc
    0.09
     ffi
    0.09
    native
    0.09
     raspberry
    0.09
     veloc
    0.09
    .tensor
    0.08
     Whe
    0.08
    Tensor
    0.08
    Act Density 0.012%

    No Known Activations