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

    Neuronpedia

    INDEX
    Explanations

    mining and miners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     impair
    1.03
     blanch
    1.01
     homeless
    0.91
     hunch
    0.91
     arah
    0.90
     engulf
    0.88
    蘋果
    0.84
    𝓃
    0.84
     dissection
    0.84
    änner
    0.84
    POSITIVE LOGITS
    ות
    1.01
     minerals
    0.90
    $\$
    0.89
    eur
    0.89
    tedir
    0.87
     ores
    0.85
    \{
    0.83
     метою
    0.82
     tempat
    0.82
     Mining
    0.81
    Act Density 0.085%

    No Known Activations