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

    Neuronpedia

    INDEX
    Explanations

    turns out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ী
    0.53
    Daemon
    0.52
     얘기를
    0.50
    Faculty
    0.50
    Producto
    0.49
    (“
    0.49
    Politics
    0.48
    ልቅ
    0.48
    所で
    0.48
    Issledovatel
    0.47
    POSITIVE LOGITS
     květ
    0.48
     exter
    0.48
     Grease
    0.46
     admissible
    0.44
     жак
    0.43
     prisión
    0.43
     grasses
    0.43
    aien
    0.43
     simpler
    0.42
     telemedicine
    0.42
    Act Density 0.000%

    No Known Activations