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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    í
    0.96
    만
    0.95
    Ï
    0.91
     mă
    0.83
     delà
    0.82
     třeba
    0.82
     undetermined
    0.81
     determines
    0.79
    ¿
    0.78
    Ñ
    0.78
    POSITIVE LOGITS
    Testing
    1.10
    damping
    1.06
    Writing
    1.05
    Snake
    1.03
     Snakes
    1.03
     Antibody
    1.03
    Carousel
    1.03
     Snake
    1.01
    Settings
    1.01
     Toolkit
    1.01
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.