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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Equal
    -0.06
     nø
    -0.06
     Ανα
    -0.06
    uae
    -0.06
    층의
    -0.06
    자를
    -0.06
     Druh
    -0.06
     cultivated
    -0.06
    	UP
    -0.06
    ants
    -0.06
    POSITIVE LOGITS
    .detect
    0.07
    orks
    0.07
    emailer
    0.06
     Array
    0.06
    ाधन
    0.06
     DateFormat
    0.06
    Observable
    0.06
     threw
    0.06
    flags
    0.06
    _TAG
    0.06
    Act Density 0.001%

    No Known Activations