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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    響
    -0.07
    им
    -0.07
     revenge
    -0.06
    )`↵
    -0.06
    QueryBuilder
    -0.06
    -role
    -0.06
    ábado
    -0.06
     Barker
    -0.06
    ette
    -0.06
    .TextView
    -0.06
    POSITIVE LOGITS
     undermines
    0.07
    ify
    0.07
     Esta
    0.07
    panied
    0.07
     NUM
    0.06
    ,min
    0.06
     बन
    0.06
    ,Integer
    0.06
     Auxiliary
    0.06
     Además
    0.06
    Act Density 0.059%

    No Known Activations