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

    Neuronpedia

    INDEX
    Explanations

    first person pronouns surrounding verbs

    oai_token-act-pair · gemini-2.0-flash

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     avoient
    -0.66
     BoxDecoration
    -0.62
     houſe
    -0.59
    MergeFrom
    -0.59
     pouvaient
    -0.58
     Houſe
    -0.58
     pédagog
    -0.56
    ijt
    -0.56
     étend
    -0.55
    Vidite
    -0.55
    POSITIVE LOGITS
     linkovi
    0.54
     resourceCulture
    0.47
     <>",
    0.46
     ab
    0.46
     jspb
    0.44
    ilent
    0.43
    ttino
    0.43
    itou
    0.42
     sub
    0.42
     jas
    0.41
    Act Density 1.288%

    No Known Activations