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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jezd
    -0.07
    ，要
    -0.07
    frica
    -0.06
    ̉
    -0.06
     grabs
    -0.06
    Late
    -0.06
    _cut
    -0.06
     damaged
    -0.06
     To
    -0.06
    DIM
    -0.06
    POSITIVE LOGITS
     for
    0.08
    γη
    0.07
     카지노
    0.07
    -for
    0.07
    Mother
    0.07
    for
    0.06
    >Name
    0.06
     Gong
    0.06
    _principal
    0.06
     натураль
    0.06
    Act Density 0.315%

    No Known Activations