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

    Neuronpedia

    INDEX
    Explanations

    there is/are/was/were

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (){
    0.21
    racting
    0.21
     Ако
    0.21
    /
    0.20
     (
    0.20
     setzt
    0.20
    .!
    0.19
    /{
    0.19
     (__
    0.19
    ized
    0.19
    POSITIVE LOGITS
     کوئی
    0.25
    कोई
    0.24
     a
    0.23
     no
    0.23
     कोई
    0.22
     keine
    0.22
     keinen
    0.21
     been
    0.21
     bedrijven
    0.20
    یک
    0.20
    Act Density 0.345%

    No Known Activations