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

    Neuronpedia

    INDEX
    Explanations

    all its / their / accounts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sorta
    0.40
     हळ
    0.38
    графія
    0.38
    kind
    0.38
    كا
    0.37
    whats
    0.37
    →</
    0.37
    ldata
    0.37
     आख
    0.36
    mirea
    0.36
    POSITIVE LOGITS
     deiner
    0.46
     practicality
    0.45
     соответ
    0.42
    ogeneity
    0.42
     perpetuity
    0.41
    实用
    0.40
     simplicity
    0.38
     práct
    0.38
     urgency
    0.38
     दवाई
    0.37
    Act Density 0.006%

    No Known Activations