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

    Neuronpedia

    INDEX
    Explanations

    formats and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    y
    0.59
    o
    0.52
    ori
    0.52
    ta
    0.50
    å
    0.50
    ider
    0.48
    UIColor
    0.48
    do
    0.47
    tt
    0.47
    oved
    0.46
    POSITIVE LOGITS
     certiorari
    0.50
     predecessor
    0.49
     Kral
    0.48
     SMART
    0.48
     complemento
    0.47
     véd
    0.47
    лением
    0.47
    雳
    0.46
     linge
    0.45
    Pra
    0.45
    Act Density 0.000%

    No Known Activations