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

    Neuronpedia

    INDEX
    Explanations

    dissolved oxygen, chemicals, minerals, gases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     trustees
    0.65
     wyd
    0.63
    য়েড
    0.63
    )
    0.63
     pays
    0.62
     sweetly
    0.61
     hod
    0.59
     sneaky
    0.59
    ু
    0.59
     dwellers
    0.58
    POSITIVE LOGITS
    l
    0.80
    v
    0.79
    S
    0.75
    h
    0.74
    G
    0.73
    ing
    0.70
    A
    0.69
    ulfanyl
    0.67
    는
    0.66
    F
    0.66
    Act Density 0.002%

    No Known Activations