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

    Neuronpedia

    INDEX
    Explanations

    sv

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ngon
    -0.07
    	damage
    -0.07
     boils
    -0.07
     crushing
    -0.07
     aftermarket
    -0.06
     Gorgeous
    -0.06
     função
    -0.06
     mounted
    -0.06
     copper
    -0.06
     Trailer
    -0.06
    POSITIVE LOGITS
     sv
    0.07
    ρωπα
    0.07
     Slave
    0.07
    .VERSION
    0.07
    ":{↵
    0.07
    ov
    0.07
    -saving
    0.06
    ovna
    0.06
     Sak
    0.06
    .ServiceModel
    0.06
    Act Density 0.006%

    No Known Activations