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

    Neuronpedia

    INDEX
    Explanations

    trained on data and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    레이
    0.50
    P
    0.49
    Hiking
    0.46
    Fax
    0.45
    S
    0.45
    Fl
    0.44
    Rey
    0.44
    물
    0.43
    E
    0.43
    ير
    0.43
    POSITIVE LOGITS
     Андроид
    0.48
    nBitCount
    0.46
     Eurostile
    0.46
     தேவையான
    0.45
    versorgung
    0.45
     finement
    0.44
     buoni
    0.44
     DeConcini
    0.44
     Surrogate
    0.43
     Rupees
    0.43
    Act Density 0.001%

    No Known Activations