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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :'',
    0.41
    :@"
    0.38
    ໄຂ
    0.37
    TaskPojo
    0.37
    ेशनों
    0.37
     advisers
    0.37
    ھیں
    0.37
    0.36
    echolog
    0.36
    ."',
    0.36
    POSITIVE LOGITS
    0.55
     =
    0.52
    /=
    0.52
    0
    0.51
     [
    0.50
     [(
    0.49
    4
    0.49
     (
    0.48
     x
    0.47
    2
    0.47
    Act Density 0.248%

    No Known Activations