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

    Neuronpedia

    INDEX
    Explanations

    concept of shift or change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     afbeelding
    0.57
    珽
    0.54
     ७
    0.51
    Saldo
    0.50
    츰
    0.50
     את
    0.50
    ੪
    0.50
    Efter
    0.50
    ｳ
    0.49
    Autres
    0.48
    POSITIVE LOGITS
     infrastructure
    0.53
     repurposed
    0.48
     cybersecurity
    0.47
     reimag
    0.47
     dozens
    0.47
    0.46
     (
    0.46
     American
    0.46
     nonprofits
    0.46
     billions
    0.45
    Act Density 0.024%

    No Known Activations