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

    Neuronpedia

    INDEX
    Explanations

    discourse markers or conjunctions

    oai_token-act-pair · gemini-2.0-flash

    because

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TagMode
    -0.98
     myſelf
    -0.90
     mxArray
    -0.84
     Theſe
    -0.83
    contentLoaded
    -0.83
     Roskov
    -0.82
     theſe
    -0.79
    RegressionTest
    -0.76
    \{\\
    -0.75
     '\\;'
    -0.75
    POSITIVE LOGITS
     perché
    0.50
    ...
    0.49
    ary
    0.49
     иначе
    0.48
     porque
    0.46
     because
    0.46
     perchè
    0.45
    gonic
    0.43
    WEBPACK
    0.43
    سر
    0.42
    Act Density 1.353%

    No Known Activations