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

    Neuronpedia

    INDEX
    Explanations

    beneficial and helpful AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     brotherhood
    0.39
    yawa
    0.38
    ارف
    0.37
     నిర్వ
    0.37
     alcoved
    0.37
    etermined
    0.37
     ہدایت
    0.36
     nigra
    0.36
     Tatha
    0.36
     artistry
    0.36
    POSITIVE LOGITS
     resilient
    0.50
    Instruments
    0.45
     Dem
    0.42
    instruments
    0.42
     Voice
    0.42
    Samb
    0.41
     Samb
    0.40
     möglichst
    0.40
     Instruments
    0.40
     ഭാഗ
    0.39
    Act Density 0.007%

    No Known Activations