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

    Neuronpedia

    INDEX
    Explanations

    sense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tk
    -0.07
    พร
    -0.07
     exploit
    -0.07
     disrespectful
    -0.07
    FLICT
    -0.06
     순
    -0.06
    (inplace
    -0.06
     nije
    -0.06
    KL
    -0.06
    (patch
    -0.06
    POSITIVE LOGITS
     sanity
    0.08
     Called
    0.07
    -thinking
    0.06
     sane
    0.06
     sensible
    0.06
    .scalablytyped
    0.06
     realistic
    0.06
    ुट
    0.06
     VERIFY
    0.06
    条
    0.06
    Act Density 0.016%

    No Known Activations