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

    Neuronpedia

    INDEX
    Explanations

    phrases about attention being given to a topic, or something turning into something.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     protoimpl
    -0.63
    TagMode
    -0.58
    jsxFileName
    -0.55
    SharedCtor
    -0.54
     oprot
    -0.53
    JspWriter
    -0.53
     ErrIntOverflow
    -0.52
    avadoc
    -0.50
    ########.
    -0.49
    ondissement
    -0.49
    POSITIVE LOGITS
     íntima
    0.60
     recuerda
    0.55
    aliana
    0.53
    strokeWidth
    0.52
    oulos
    0.51
    σμα
    0.50
     cardinals
    0.50
    țiuni
    0.50
    oding
    0.50
     RHS
    0.49
    Act Density 2.481%

    No Known Activations