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

    Neuronpedia

    INDEX
    Explanations

    biodegradable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    floor
    0.53
    One
    0.52
     floor
    0.52
     inline
    0.51
    I
    0.50
     двор
    0.49
    We
    0.48
    E
    0.47
     box
    0.47
    ur
    0.46
    POSITIVE LOGITS
    ຼ
    0.56
     Су
    0.53
     gepub
    0.53
    hidrat
    0.53
    0.53
     배
    0.52
    setNome
    0.52
    𒀝
    0.52
    Рис
    0.51
    흐
    0.51
    Act Density 0.000%

    No Known Activations