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

    Neuronpedia

    INDEX
    Explanations

    Doing

    np_max-act · gemini-2.0-flash

    This neuron responds to verbs describing game actions or mechanics (e.g., upgrading, invading, pillaging).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    forg
    -0.06
     роботу
    -0.06
     affinity
    -0.06
     Bilg
    -0.06
     regenerated
    -0.06
     noct
    -0.06
     MULTI
    -0.06
     Gram
    -0.06
     unequal
    -0.06
     ב
    -0.06
    POSITIVE LOGITS
    톡
    0.06
     wore
    0.06
     arrangements
    0.06
     Newtown
    0.06
     ราย
    0.06
    ppelin
    0.06
    аза
    0.06
    Singapore
    0.06
    rock
    0.06
     тоже
    0.06
    Act Density 0.323%

    No Known Activations