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

    Neuronpedia

    INDEX
    Explanations

    Software and blocking content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Justin
    -0.09
     Hawkins
    -0.08
    umbotron
    -0.08
     الإسلام
    -0.08
    Ow
    -0.08
     imu
    -0.08
     atmosfera
    -0.08
    成年人
    -0.08
     �
    -0.07
     Aguil
    -0.07
    POSITIVE LOGITS
     install
    0.09
     solids
    0.08
     conject
    0.08
     Reduc
    0.08
    .install
    0.08
     Install
    0.08
     adds
    0.08
     ಮೂಲಕ
    0.08
     reduct
    0.08
     installer
    0.08
    Act Density 0.008%

    No Known Activations