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

    Neuronpedia

    INDEX
    Explanations

    knot, sunflowers, dress, tried, wears

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ard
    0.37
    basis
    0.37
    ings
    0.36
     hospitality
    0.36
    intervention
    0.36
     bosom
    0.36
     religiosas
    0.36
    😊
    0.36
    閨
    0.36
    Ard
    0.36
    POSITIVE LOGITS
    жного
    0.42
     tjän
    0.41
     tumbuh
    0.38
     Rooster
    0.38
    比较
    0.37
     jähr
    0.37
     Jour
    0.37
    মুর
    0.37
     Predator
    0.37
     -->'
    0.37
    Act Density 0.000%

    No Known Activations