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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oster
    -0.06
    .fixture
    -0.06
    ’il
    -0.06
    libft
    -0.06
     имеет
    -0.06
    руж
    -0.06
    Alright
    -0.06
    aw
    -0.06
     Тому
    -0.06
     особливо
    -0.06
    POSITIVE LOGITS
    (target
    0.07
     pocket
    0.06
     REPL
    0.06
     ©
    0.06
    (view
    0.06
    .Section
    0.06
     sl
    0.06
    _u
    0.06
    @@
    0.06
     TIMER
    0.06
    Act Density 0.034%

    No Known Activations