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

    Neuronpedia

    INDEX
    Explanations

    prevent the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    igné
    1.07
    aient
    1.02
    ्स
    1.02
    een
    1.02
    fait
    1.02
    ٕ
    1.01
    ilikom
    1.00
    ̝
    0.99
    e
    0.98
    guh
    0.97
    POSITIVE LOGITS
     Introduce
    1.16
    afficher
    1.15
    ंह
    1.12
     jaaye
    1.12
     afficher
    1.11
     temat
    1.10
    ተ
    1.07
     кре
    1.07
     hashtags
    1.05
     headwinds
    1.04
    Act Density 0.005%

    No Known Activations