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

    Neuronpedia

    INDEX
    Explanations

    >

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    不知道
    -0.07
    	js
    -0.07
     debuted
    -0.06
     احساس
    -0.06
    -built
    -0.06
    Internal
    -0.06
     liberated
    -0.06
    واع
    -0.06
    \"><
    -0.06
    peated
    -0.06
    POSITIVE LOGITS
    Unmarshaller
    0.06
     Pornhub
    0.06
    .position
    0.05
    .Ş
    0.05
    >E
    0.05
    追
    0.05
     düşür
    0.05
    ouple
    0.05
    ۱۹۹
    0.05
    *******
↵
    0.05
    Act Density 0.293%

    No Known Activations