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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     정확
    -0.07
    /***************************************************************************↵
    -0.06
    一步
    -0.06
    =b
    -0.06
     CFO
    -0.06
    ňují
    -0.06
    state
    -0.06
    State
    -0.06
    (Utils
    -0.06
    pee
    -0.06
    POSITIVE LOGITS
    hot
    0.07
    .sorted
    0.07
    AFP
    0.06
     normally
    0.06
     tradition
    0.06
    uevo
    0.06
    .FLOAT
    0.06
     glitches
    0.06
    array
    0.06
     usually
    0.06
    Act Density 0.013%

    No Known Activations