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

    Neuronpedia

    INDEX
    Explanations

    both

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eagle
    -0.08
    izont
    -0.08
     Gry
    -0.07
    easy
    -0.07
    仮
    -0.07
    .exp
    -0.07
    /day
    -0.07
     май
    -0.06
     simple
    -0.06
     easy
    -0.06
    POSITIVE LOGITS
     both
    0.19
     Both
    0.14
    Both
    0.14
    both
    0.13
     BOTH
    0.13
    :both
    0.10
     neither
    0.09
    _BOTH
    0.08
     all
    0.08
    Neither
    0.08
    Act Density 0.048%

    No Known Activations