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

    Neuronpedia

    INDEX
    Explanations

    is are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     velocity
    -0.06
     hull
    -0.06
     Digest
    -0.06
     rescued
    -0.06
    GA
    -0.06
    frac
    -0.06
     tranh
    -0.06
    zin
    -0.05
    �
    -0.05
    ():
    -0.05
    POSITIVE LOGITS
     Recommend
    0.07
    ้าก
    0.07
    .ic
    0.07
    (non
    0.07
    (routes
    0.07
     Ideally
    0.07
     YES
    0.07
     distinctive
    0.06
     ammunition
    0.06
    "Well
    0.06
    Act Density 0.071%

    No Known Activations