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

    Neuronpedia

    INDEX
    Explanations

    discuss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     уход
    -0.07
     limits
    -0.07
    (copy
    -0.07
     mantle
    -0.07
    {id
    -0.07
     penalties
    -0.07
     potentials
    -0.07
    的事情
    -0.07
     felt
    -0.07
    kový
    -0.07
    POSITIVE LOGITS
     discuss
    0.15
     discussion
    0.14
     discussing
    0.14
     discussed
    0.13
     discussions
    0.11
     discusses
    0.10
    Discuss
    0.10
    Discussion
    0.10
     Discuss
    0.09
     Discussion
    0.09
    Act Density 0.025%

    No Known Activations