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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .say
    -0.07
    usual
    -0.06
    .draw
    -0.06
    雲
    -0.06
    督
    -0.06
    (super
    -0.06
    .Sound
    -0.06
    長
    -0.06
    สม
    -0.06
     山
    -0.06
    POSITIVE LOGITS
     TICK
    0.08
     Sergei
    0.07
     että
    0.07
     Tactics
    0.07
     ekip
    0.07
    (TypeError
    0.07
     COUNTY
    0.07
     usar
    0.06
    .WaitFor
    0.06
     ")");↵
    0.06
    Act Density 0.001%

    No Known Activations