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

    Neuronpedia

    INDEX
    Explanations

    warm water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Number
    0.98
    Digest
    0.91
    Dent
    0.89
    Collect
    0.88
    ל
    0.88
    Time
    0.87
    Prz
    0.83
    Dig
    0.82
    umpy
    0.82
    Doctors
    0.79
    POSITIVE LOGITS
     rings
    0.80
     SOI
    0.79
     MRC
    0.78
     produ
    0.77
     Staphylococcus
    0.77
     "(
    0.76
    ت
    0.76
     BHK
    0.75
     defect
    0.75
    㧿
    0.75
    Act Density 0.001%

    No Known Activations