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

    Neuronpedia

    INDEX
    Explanations

    time duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $username
    -0.07
     asshole
    -0.06
     Uma
    -0.06
    χα
    -0.06
    anela
    -0.06
     MySqlConnection
    -0.06
    nějších
    -0.06
     erotici
    -0.06
    51
    -0.06
    инки
    -0.06
    POSITIVE LOGITS
     years
    0.08
    	person
    0.08
     низ
    0.07
    三年
    0.07
     minutes
    0.07
     Students
    0.07
    бот
    0.07
    воз
    0.07
     trois
    0.07
     anon
    0.07
    Act Density 0.038%

    No Known Activations