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

    Neuronpedia

    INDEX
    Explanations

    interests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ตอน
    -0.07
     trong
    -0.07
     follow
    -0.07
    К
    -0.06
    omial
    -0.06
    nk
    -0.06
    卿
    -0.06
     nelle
    -0.06
    gether
    -0.06
    聞
    -0.06
    POSITIVE LOGITS
     goalkeeper
    0.08
     severed
    0.07
     Theatre
    0.07
    (ep
    0.07
     Broker
    0.07
     excuses
    0.07
     hát
    0.07
    Profiles
    0.07
     interests
    0.07
    —at
    0.07
    Act Density 0.010%

    No Known Activations