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

    Neuronpedia

    INDEX
    Explanations

    internal affairs and control

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     assembly
    0.50
     T
    0.49
     F
    0.48
    ümer
    0.45
     Assembly
    0.45
    F
    0.45
     touchscreen
    0.44
    ha
    0.43
     flu
    0.43
     feud
    0.43
    POSITIVE LOGITS
    ផ្
    0.48
    )$:
    0.46
     luminoso
    0.44
    水の
    0.43
    कॉइन
    0.42
    ној
    0.42
     ponemos
    0.42
    চনায়
    0.42
    лых
    0.41
    水を
    0.40
    Act Density 0.002%

    No Known Activations