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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Inc
    -0.07
    ekil
    -0.07
     �
    -0.07
    ducers
    -0.06
    hape
    -0.06
     Deutsch
    -0.06
     độc
    -0.06
    tid
    -0.06
    mod
    -0.06
    unnable
    -0.06
    POSITIVE LOGITS
     coax
    0.06
     юрид
    0.06
     огля
    0.06
     صفحه
    0.06
     required
    0.06
     Enabled
    0.06
    /tcp
    0.06
     officially
    0.06
     còn
    0.06
    SCRIPTOR
    0.06
    Act Density 0.016%

    No Known Activations