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

    Neuronpedia

    INDEX
    Explanations

    question mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     validators
    -0.08
    .streaming
    -0.07
    /hr
    -0.07
     adulthood
    -0.07
     leap
    -0.06
     Rider
    -0.06
    (UnmanagedType
    -0.06
    lanır
    -0.06
     пош
    -0.06
     ương
    -0.06
    POSITIVE LOGITS
    Area
    0.07
    _san
    0.06
    Mi
    0.06
    -items
    0.06
     adress
    0.06
     Writing
    0.06
    Needed
    0.06
     ince
    0.06
     Solution
    0.06
     APPLY
    0.06
    Act Density 0.041%

    No Known Activations