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

    Neuronpedia

    INDEX
    Explanations

    }

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     butcher
    -0.07
     }};↵
    -0.07
    POL
    -0.07
    日の
    -0.06
    isor
    -0.06
    +");↵
    -0.06
    620
    -0.06
    _pr
    -0.06
    PRS
    -0.06
    lesson
    -0.06
    POSITIVE LOGITS
     React
    0.07
     prom
    0.07
     constituency
    0.07
     Validates
    0.06
     Abuse
    0.06
     CONTACT
    0.06
     informant
    0.06
     appetite
    0.06
    -create
    0.06
     KIND
    0.06
    Act Density 0.001%

    No Known Activations