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

    Neuronpedia

    INDEX
    Explanations

    reliance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gates
    -0.08
    emploi
    -0.07
    $date
    -0.06
    tır
    -0.06
    endment
    -0.06
    ette
    -0.06
    (edges
    -0.06
    -ps
    -0.06
    buff
    -0.06
    zm
    -0.06
    POSITIVE LOGITS
    (rad
    0.07
     Cleanup
    0.07
     hai
    0.06
     вним
    0.06
     Elliot
    0.06
    :{
↵
    0.06
    _editor
    0.06
    平成
    0.06
     سه
    0.06
     Obama
    0.06
    Act Density 0.003%

    No Known Activations