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

    Neuronpedia

    INDEX
    Explanations

    milk

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Walker
    -0.07
     LIGHT
    -0.07
     LED
    -0.06
    endir
    -0.06
     shifting
    -0.06
    IGH
    -0.06
     Thread
    -0.06
    高速
    -0.06
    ADD
    -0.06
     دستور
    -0.06
    POSITIVE LOGITS
    .do
    0.07
     hurts
    0.06
     února
    0.06
    ressing
    0.06
    ma
    0.06
    tober
    0.06
    ¢
    0.06
     ########################
    0.06
    ,!
    0.06
    แรก
    0.06
    Act Density 0.002%

    No Known Activations