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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Increasing
    -0.07
    "].
    -0.06
    descending
    -0.06
    belief
    -0.06
     Increasing
    -0.06
     secondo
    -0.06
    'int
    -0.06
    561
    -0.06
    927
    -0.06
     seem
    -0.06
    POSITIVE LOGITS
    \Desktop
    0.07
     Trotsky
    0.07
     Covid
    0.07
    (enable
    0.07
    (dictionary
    0.07
    loquent
    0.07
     aspect
    0.07
    lice
    0.06
    (filePath
    0.06
    .basename
    0.06
    Act Density 0.064%

    No Known Activations