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

    Neuronpedia

    INDEX
    Explanations

    percentiles and numbers above fifty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contact
    -0.92
    icali
    -0.82
    接触
    -0.82
     Christiane
    -0.81
     contacts
    -0.81
    contact
    -0.81
     twofold
    -0.79
    창
    -0.76
     contatto
    -0.76
    dett
    -0.75
    POSITIVE LOGITS
     Ninety
    1.58
     ninety
    1.45
    9
    1.36
    Nin
    1.14
     Eighty
    1.05
     Seventy
    1.02
     eighty
    1.01
    Fifty
    1.00
     ninth
    0.96
    ₉
    0.88
    Act Density 0.036%

    No Known Activations