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

    Neuronpedia

    INDEX
    Explanations

    upload files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     │
    0.41
     Pener
    0.41
     ......
    0.40
     அழை
    0.39
     ........
    0.38
    桕
    0.38
     Members
    0.38
    ';...
    0.37
     .......
    0.37
     []
    0.37
    POSITIVE LOGITS
    город
    0.38
     आरोपों
    0.37
    estimating
    0.37
     ऑफिश
    0.37
    trained
    0.36
     positif
    0.36
    6
    0.36
    ittä
    0.36
     positivo
    0.35
    ilitas
    0.35
    Act Density 0.000%

    No Known Activations