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

    Neuronpedia

    INDEX
    Explanations

    decision-making

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Session
    -0.07
     Kingdom
    -0.06
     poem
    -0.06
     |-
    -0.06
     вір
    -0.06
     Chest
    -0.06
     Kv
    -0.06
     honoured
    -0.06
     formulated
    -0.06
    -Clause
    -0.06
    POSITIVE LOGITS
     stabbing
    0.06
    nehmen
    0.06
    ционного
    0.06
     GetType
    0.06
    ㅠㅠ
    0.06
    leneck
    0.06
     Bringing
    0.06
     <=>
    0.06
     unsigned
    0.06
    ....
    0.06
    Act Density 0.099%

    No Known Activations