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
     perverse
    -0.06
     glo
    -0.06
    compressed
    -0.06
     Checker
    -0.06
    Flo
    -0.06
     eq
    -0.06
    mse
    -0.06
    	Test
    -0.06
     pleasures
    -0.06
    Cr
    -0.06
    POSITIVE LOGITS
     ARP
    0.07
    ，↵
    0.06
     Hük
    0.06
    .ver
    0.06
    },↵↵
    0.06
    <AM
    0.06
     สร
    0.06
     Ã
    0.06
     Modal
    0.06
     αυτό
    0.06
    Act Density 0.029%

    No Known Activations