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

    Neuronpedia

    INDEX
    Explanations

    Steps, procedures, aims

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    buff
    -0.07
    _CONV
    -0.07
    EXPECT
    -0.07
     最
    -0.07
     diapers
    -0.06
    .stock
    -0.06
     misguided
    -0.06
     Roose
    -0.06
     myList
    -0.06
     stays
    -0.06
    POSITIVE LOGITS
    +"]
    0.07
     #$
    0.06
    '];?>↵
    0.06
     */
↵
    0.06
    )">↵
    0.06
     qa
    0.06
     }?>↵
    0.06
    /yyyy
    0.06
    ">↵↵↵
    0.06
    }]↵
    0.06
    Act Density 0.094%

    No Known Activations