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

    Neuronpedia

    INDEX
    Explanations

    references to searching or searches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    searching for something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lukewarm
    -0.54
    atem
    -0.52
     Bevan
    -0.51
    entlicher
    -0.51
     Momentum
    -0.49
    idey
    -0.49
    #%%
    -0.49
    TITUDE
    -0.48
    ecma
    -0.48
     Bett
    -0.48
    POSITIVE LOGITS
     search
    1.25
     Search
    1.09
     SEARCH
    1.01
    search
    0.94
    Search
    0.90
    SEARCH
    0.84
     searches
    0.79
     searched
    0.77
     searching
    0.77
     Searches
    0.73
    Act Density 0.011%

    No Known Activations