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

    Neuronpedia

    INDEX
    Explanations

    provides concise quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     newMovie
    0.47
     valide
    0.42
    Retail
    0.41
    wny
    0.40
     করি
    0.39
     niche
    0.39
     今回
    0.39
     产品
    0.39
     retail
    0.38
     niches
    0.38
    POSITIVE LOGITS
     Sugar
    0.40
    ̈
    0.37
     Rais
    0.37
     planing
    0.37
    jela
    0.36
    Ư
    0.36
     Lact
    0.36
     raisins
    0.36
     HAZ
    0.36
    item
    0.35
    Act Density 0.000%

    No Known Activations