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

    Neuronpedia

    INDEX
    Explanations

    certain

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on the hedge word “certain,” flagging qualifying or tentative statements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     playoffs
    -0.08
    launch
    -0.07
    ripple
    -0.07
    ัวอย
    -0.07
    只是
    -0.07
     leaps
    -0.07
    746
    -0.07
    ピ
    -0.06
     персп
    -0.06
    пе
    -0.06
    POSITIVE LOGITS
     certain
    0.14
    Certain
    0.12
     Certain
    0.12
     ein
    0.08
    某
    0.08
     an
    0.08
     Rat
    0.07
     Kenneth
    0.07
    .den
    0.07
     Cath
    0.07
    Act Density 0.019%

    No Known Activations