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

    Neuronpedia

    INDEX
    Explanations

    compet, Dor, refer, prefer, diner, been, leg, fin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ân
    0.40
    тия
    0.39
     Vaughan
    0.38
    ટે
    0.37
    테
    0.37
     commitments
    0.37
    ibert
    0.36
     साव
    0.36
    andria
    0.36
     Bert
    0.36
    POSITIVE LOGITS
    inta
    0.78
    inte
    0.55
    ints
    0.50
     Pinto
    0.48
    inn
    0.47
    INTE
    0.45
    arin
    0.43
    їн
    0.43
    intă
    0.43
    iint
    0.43
    Act Density 0.002%

    No Known Activations