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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oo
    -0.07
     cosm
    -0.07
     foresee
    -0.07
    export
    -0.06
     interfere
    -0.06
     Some
    -0.06
    phi
    -0.06
     archive
    -0.06
     bất
    -0.06
    ческих
    -0.06
    POSITIVE LOGITS
    1
    0.18
    １
    0.12
    ۱
    0.09
    १
    0.09
    2
    0.09
    01
    0.09
    001
    0.08
    ml
    0.08
    ３
    0.08
    0
    0.07
    Act Density 0.654%

    No Known Activations