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

    Neuronpedia

    INDEX
    Explanations

    keep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bobby
    -0.08
    كو
    -0.07
     airborne
    -0.07
    _bill
    -0.07
    lined
    -0.07
    FRING
    -0.07
    France
    -0.06
    _ber
    -0.06
     Frame
    -0.06
    ],
↵
    -0.06
    POSITIVE LOGITS
     (“
    0.06
     esta
    0.06
    TU
    0.06
     समस
    0.06
     уд
    0.06
    _dark
    0.06
    AU
    0.06
     remain
    0.06
     kept
    0.06
     रख
    0.06
    Act Density 0.023%

    No Known Activations