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

    Neuronpedia

    INDEX
    Explanations

    explain code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Wil
    0.93
     Wilkinson
    0.92
    <0x8E>
    0.91
     potter
    0.89
     Antonia
    0.86
     MTT
    0.83
    漓
    0.83
     Schilling
    0.82
     Pompeo
    0.82
    villa
    0.82
    POSITIVE LOGITS
     Code
    2.35
     code
    2.28
    Code
    2.28
     codes
    2.24
     Codes
    2.22
    code
    2.19
    Codes
    2.16
     Coding
    2.05
     coding
    2.01
    codes
    1.96
    Act Density 0.615%

    No Known Activations