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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dışı
    -0.07
    _sel
    -0.07
     onset
    -0.06
     letting
    -0.06
    etro
    -0.06
     anyways
    -0.06
    450
    -0.06
     Foam
    -0.06
    純
    -0.06
    	number
    -0.06
    POSITIVE LOGITS
    .Test
    0.07
    े।↵
    0.07
     signifies
    0.07
     Chinese
    0.06
     dissatisfaction
    0.06
    ndern
    0.06
    345
    0.06
    ”.↵↵
    0.06
     Confirmation
    0.06
    Contracts
    0.06
    Act Density 0.005%

    No Known Activations