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

    Neuronpedia

    INDEX
    Explanations

    Special characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <W
    -0.07
    fault
    -0.07
    „P
    -0.07
    ød
    -0.06
    lık
    -0.06
    join
    -0.06
     ödem
    -0.06
     irony
    -0.06
     *
↵
    -0.06
     Cathedral
    -0.06
    POSITIVE LOGITS
     [<
    0.06
     вважа
    0.06
    erture
    0.06
     cbd
    0.06
    (optimizer
    0.06
    google
    0.06
     اینکه
    0.06
    丶
    0.05
    ศจ
    0.05
    Putting
    0.05
    Act Density 0.005%

    No Known Activations