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

    Neuronpedia

    INDEX
    Explanations

    physical location

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ались
    -0.08
     эп
    -0.07
     bmp
    -0.07
     portrait
    -0.07
     titles
    -0.07
     uncovered
    -0.06
     specialists
    -0.06
    -story
    -0.06
    وري
    -0.06
    یک
    -0.06
    POSITIVE LOGITS
    llib
    0.07
    ivent
    0.06
     proletariat
    0.06
     Penal
    0.06
    .coord
    0.06
    cpf
    0.06
     pornofil
    0.06
    daf
    0.06
     homem
    0.06
    .assertIs
    0.06
    Act Density 0.137%

    No Known Activations