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

    Neuronpedia

    INDEX
    Explanations

    Should

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word "should" (as in conditional recommendations or hypothetical questions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    iele
    -0.07
     balcony
    -0.07
    گیرد
    -0.07
    уже
    -0.06
    }:
    -0.06
     image
    -0.06
     onion
    -0.06
    except
    -0.06
    Frame
    -0.06
    Banner
    -0.06
    POSITIVE LOGITS
     직접
    0.07
    ูม
    0.06
     규
    0.06
     %%↵
    0.06
    oron
    0.06
    {text
    0.06
    ;$
    0.06
    대비
    0.06
     converse
    0.06
     (**
    0.06
    Act Density 0.014%

    No Known Activations