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

    Neuronpedia

    INDEX
    Explanations

    ld

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _VAR
    -0.07
     Доб
    -0.07
    ?>:</
    -0.06
    _PRESS
    -0.06
    誉
    -0.06
    .TODO
    -0.06
     массив
    -0.06
     Ц
    -0.06
    _fl
    -0.06
    toHave
    -0.06
    POSITIVE LOGITS
     although
    0.07
     multi
    0.07
     plug
    0.06
    .bed
    0.06
     �
    0.06
     XPAR
    0.06
    _multi
    0.06
     solution
    0.06
     Patron
    0.06
     story
    0.06
    Act Density 0.000%

    No Known Activations