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

    Neuronpedia

    INDEX
    Explanations

    Increase

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the word “Increase” (often as the first word of a heading or sentence).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    44
    -0.07
     mind
    -0.07
     pid
    -0.07
    707
    -0.07
     PART
    -0.07
     Pad
    -0.07
     fid
    -0.07
     topic
    -0.07
     Bord
    -0.06
     Panel
    -0.06
    POSITIVE LOGITS
     increase
    0.16
     increasing
    0.15
     increased
    0.14
     Increase
    0.13
    incre
    0.13
    increase
    0.12
     increases
    0.12
    Increased
    0.11
    Increase
    0.11
     decrease
    0.11
    Act Density 0.072%

    No Known Activations