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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    slots
    -0.07
     contemplate
    -0.07
    rical
    -0.06
     гип
    -0.06
    ($"
    -0.06
    lymp
    -0.06
    _passed
    -0.06
     scl
    -0.06
     massasje
    -0.06
     Ment
    -0.06
    POSITIVE LOGITS
    money
    0.07
     金
    0.07
    ивать
    0.06
    $content
    0.06
    /q
    0.06
    овой
    0.06
    Tonight
    0.06
     	↵
    0.06
    енность
    0.06
     Census
    0.06
    Act Density 0.066%

    No Known Activations