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

    Neuronpedia

    INDEX
    Explanations

    mobile

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     peaceful
    -0.07
     operators
    -0.07
     seeds
    -0.07
    byt
    -0.07
     freezes
    -0.07
     ли
    -0.07
     tense
    -0.06
     wm
    -0.06
    threshold
    -0.06
     voter
    -0.06
    POSITIVE LOGITS
     contenu
    0.06
    用品
    0.06
     Uncomment
    0.06
    iferay
    0.06
     prze
    0.06
    Bindable
    0.06
     Lady
    0.06
    retry
    0.06
     khám
    0.06
     erotische
    0.06
    Act Density 0.040%

    No Known Activations