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

    Neuronpedia

    INDEX
    Explanations

    changes over time

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     üy
    -0.07
    üt
    -0.07
     Nacht
    -0.07
    {:
    -0.06
     ruku
    -0.06
     Kostenlos
    -0.06
     vzděl
    -0.06
    bero
    -0.06
    larına
    -0.06
     Alexand
    -0.06
    POSITIVE LOGITS
     代
    0.06
     �
    0.06
    VENTORY
    0.06
    Finished
    0.06
    決
    0.06
     MATCH
    0.06
     الض
    0.06
    _classification
    0.06
     Antarctic
    0.06
    ไฟล
    0.06
    Act Density 0.002%

    No Known Activations