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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    乡
    -0.07
    ACCOUNT
    -0.07
    reward
    -0.06
     STUD
    -0.06
    println
    -0.06
    	esc
    -0.06
     Governments
    -0.06
    &A
    -0.06
    .randomUUID
    -0.06
    practice
    -0.06
    POSITIVE LOGITS
    imedia
    0.07
     dotted
    0.06
    ůj
    0.06
    iệp
    0.06
    anca
    0.06
     заходів
    0.06
    �
    0.06
    _MISS
    0.06
     SCM
    0.06
     ={
    0.06
    Act Density 0.037%

    No Known Activations