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

    Neuronpedia

    INDEX
    Explanations

    More Fundamentals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imerk
    0.28
     fleets
    0.27
    咚
    0.26
     Rubio
    0.25
    echolog
    0.25
    inic
    0.25
    dale
    0.24
    inline
    0.24
     assistenza
    0.24
     ketchup
    0.24
    POSITIVE LOGITS
     Physical
    0.29
    Physical
    0.28
     Sensory
    0.26
    owness
    0.25
     Vibration
    0.24
     Shakti
    0.24
     Perception
    0.23
    LDA
    0.23
     perceives
    0.23
     (
    0.23
    Act Density 0.000%

    No Known Activations