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

    Neuronpedia

    INDEX
    Explanations

    GUI code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Plants
    0.52
     Designers
    0.51
     Fires
    0.46
     prettiest
    0.45
     powerplant
    0.45
     Angleterre
    0.45
     designers
    0.44
     Girls
    0.44
     Cycle
    0.44
     Pantry
    0.44
    POSITIVE LOGITS
     effectual
    0.40
    伌
    0.40
     автомоби
    0.38
    iscal
    0.37
     subject
    0.37
     subsum
    0.36
    моби
    0.36
    exponent
    0.36
     sprach
    0.35
    Lus
    0.35
    Act Density 0.002%

    No Known Activations