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

    Neuronpedia

    INDEX
    Explanations

    research implications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _cs
    -0.06
    many
    -0.06
     */
    -0.06
    (Tag
    -0.06
     cams
    -0.06
     Arbeits
    -0.06
    侯
    -0.06
    .Elements
    -0.06
    ened
    -0.06
    agate
    -0.06
    POSITIVE LOGITS
     qual
    0.07
     простран
    0.06
     Fall
    0.06
     toto
    0.06
     UA
    0.06
    _SCREEN
    0.06
     tome
    0.06
    MAND
    0.06
    تن
    0.06
     learner
    0.06
    Act Density 0.044%

    No Known Activations