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

    Neuronpedia

    INDEX
    Explanations

    two

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ISC
    -0.07
     Nevada
    -0.07
    wan
    -0.06
     triples
    -0.06
    pieces
    -0.06
     suffix
    -0.06
    IZATION
    -0.06
     flavored
    -0.06
    rows
    -0.06
    Life
    -0.06
    POSITIVE LOGITS
    	Expect
    0.07
    ."""
    0.06
     нарез
    0.06
     tast
    0.06
     representa
    0.06
     bravery
    0.06
    .maps
    0.06
    届
    0.06
     Compet
    0.06
    (pad
    0.06
    Act Density 0.050%

    No Known Activations