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

    Neuronpedia

    INDEX
    Explanations

    prepositions/quantifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Boulevard
    -0.06
    $")↵
    -0.06
     Blvd
    -0.06
     decltype
    -0.06
    .Formatter
    -0.06
     одной
    -0.06
    .ContentAlignment
    -0.06
     DRIVER
    -0.06
     Gloves
    -0.05
    _management
    -0.05
    POSITIVE LOGITS
    etermination
    0.07
     外
    0.07
     Cork
    0.06
     indifference
    0.06
     adjusted
    0.06
     جن
    0.06
    jectory
    0.06
     laisse
    0.06
    广
    0.06
    iena
    0.06
    Act Density 0.076%

    No Known Activations