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

    Neuronpedia

    INDEX
    Explanations

    describing or querying information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     нәрсә
    0.52
     traum
    0.41
    Computed
    0.40
    শরণ
    0.39
     übertragen
    0.39
    மைக்
    0.39
    Oregon
    0.38
    ాత్ర
    0.38
     конф
    0.38
     Oregon
    0.38
    POSITIVE LOGITS
    Describe
    0.61
     describe
    0.61
     Describe
    0.60
    describe
    0.57
     describ
    0.54
     Put
    0.53
     описы
    0.51
     put
    0.48
     describes
    0.48
     describing
    0.48
    Act Density 0.016%

    No Known Activations