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

    Neuronpedia

    INDEX
    Explanations

    the verb "to be" in various tenses

    oai_token-act-pair · gemini-2.0-flash

    general news/text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Face
    -0.64
     face
    -0.60
    Face
    -0.59
     resourceCulture
    -0.59
    face
    -0.56
     Faces
    -0.56
     FACE
    -0.54
    faced
    -0.54
     faced
    -0.53
    phosa
    -0.52
    POSITIVE LOGITS
     ModelRenderer
    0.66
     Wiktionnaire
    0.60
    éric
    0.53
    giphy
    0.52
     setCurrent
    0.52
     appui
    0.52
    opsida
    0.51
     ErrInvalid
    0.51
    ModelSerializer
    0.51
     dAtA
    0.50
    Act Density 9.914%

    No Known Activations