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

    Neuronpedia

    INDEX
    Explanations

    goal

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting statements of purpose or objectives—phrases like “Our goal is to…” or “My goal is to….”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Customers
    -0.07
     acquitted
    -0.06
    herits
    -0.06
     ﾞ
    -0.06
    (tokens
    -0.06
     шляхом
    -0.06
     арх
    -0.06
     rejected
    -0.06
    (tt
    -0.06
     Restrictions
    -0.06
    POSITIVE LOGITS
     Ethan
    0.07
    snake
    0.07
    trecht
    0.06
    carrier
    0.06
    σματα
    0.06
    イヤ
    0.06
    izzly
    0.06
     octave
    0.06
    (sym
    0.06
    骑
    0.06
    Act Density 0.020%

    No Known Activations