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

    Neuronpedia

    INDEX
    Explanations

    Commas and periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    winter
    -0.07
    Sessions
    -0.07
    Areas
    -0.06
    っぱ
    -0.06
     завод
    -0.06
     torque
    -0.06
    endTime
    -0.06
     Provid
    -0.06
     avoids
    -0.06
    Buttons
    -0.06
    POSITIVE LOGITS
    Messaging
    0.07
     GPLv
    0.07
    _FONT
    0.07
     للإ
    0.07
     �
    0.06
     titleLabel
    0.06
    ++++
    0.06
     --↵
    0.06
     normalize
    0.06
    -в
    0.06
    Act Density 0.003%

    No Known Activations