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

    Neuronpedia

    INDEX
    Explanations

    Date and time formats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ʥ
    -0.07
    谷爱
    -0.07
     пользу
    -0.07
    Tes
    -0.07
    Power
    -0.07
     Review
    -0.07
     compassionate
    -0.07
    .asp
    -0.07
     Report
    -0.06
    -Owned
    -0.06
    POSITIVE LOGITS
     deja
    0.07
     kra
    0.07
    就已经
    0.07
    _Anim
    0.06
    �
    0.06
    到现在
    0.06
    FromClass
    0.06
    ই
    0.06
    クロ
    0.06
     attendees
    0.06
    Act Density 0.003%

    No Known Activations