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

    Neuronpedia

    INDEX
    Explanations

    code/computer content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    published
    -0.07
     ************************************************************************
    -0.07
    .oracle
    -0.07
    DOG
    -0.06
     indifferent
    -0.06
    instruction
    -0.06
    rug
    -0.06
    -slot
    -0.06
    clock
    -0.06
    isbn
    -0.06
    POSITIVE LOGITS
    ζει
    0.06
     STDMETHODCALLTYPE
    0.06
     تلویزیون
    0.06
    (".");↵
    0.06
     ولم
    0.06
    олі
    0.06
    자는
    0.06
    scribers
    0.06
    ял
    0.06
     Voice
    0.06
    Act Density 0.270%

    No Known Activations