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

    Neuronpedia

    INDEX
    Explanations

    \

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     качестве
    -0.08
    清爽
    -0.07
     |>
    -0.07
    ♑
    -0.07
    作为一种
    -0.07
    צמח
    -0.07
    ⇐
    -0.07
    %)↵↵
    -0.07
    _cod
    -0.07
    >%
    -0.07
    POSITIVE LOGITS
     vene
    0.07
    ราว
    0.07
    MESS
    0.07
     linen
    0.07
    _hashes
    0.07
    ов
    0.07
    煓
    0.07
    .rnn
    0.07
    onomy
    0.06
    greg
    0.06
    Act Density 0.001%

    No Known Activations