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

    Neuronpedia

    INDEX
    Explanations

    code, tutorials

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’”
    -0.66
    Portale
    -0.63
    ?“
    -0.63
     ?”
    -0.62
    ?”,
    -0.61
     betweenstory
    -0.61
     nahilalakip
    -0.61
    stdc
    -0.61
    colades
    -0.61
    ’?
    -0.60
    POSITIVE LOGITS
     information
    0.54
     Operation
    0.46
     everything
    0.46
     info
    0.45
    Master
    0.45
     masters
    0.45
     aí
    0.44
     
    0.43
     thorough
    0.43
    Body
    0.43
    Act Density 0.007%

    No Known Activations