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

    Neuronpedia

    INDEX
    Explanations

    Commentary/Reflections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ############
    -0.08
    amen
    -0.08
    acons
    -0.07
    .NotNil
    -0.07
    τολ
    -0.06
     Vec
    -0.06
    피
    -0.06
     Engagement
    -0.06
     Interaction
    -0.06
    ，比
    -0.06
    POSITIVE LOGITS
     Александр
    0.06
     klub
    0.06
    ehir
    0.06
    ernals
    0.06
    ibus
    0.06
     clin
    0.06
     kred
    0.06
     Kent
    0.06
     restructuring
    0.06
     pst
    0.06
    Act Density 0.083%

    No Known Activations