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

    Neuronpedia

    INDEX
    Explanations

    save and extract

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Themen
    0.80
     rumour
    0.80
     lentement
    0.79
     पढ़ेंगे
    0.78
     nějak
    0.78
     courbes
    0.76
     themed
    0.76
     tumult
    0.76
    моби
    0.75
    ંતુ
    0.75
    POSITIVE LOGITS
    Save
    0.78
    sole
    0.77
    remove
    0.76
    save
    0.76
    Remove
    0.75
     extracted
    0.74
    stri
    0.72
     Save
    0.72
     Remove
    0.71
    join
    0.70
    Act Density 0.426%

    No Known Activations