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

    Neuronpedia

    INDEX
    Explanations

    source

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -$
    -0.07
     realism
    -0.06
    nger
    -0.06
     juni
    -0.06
     drafted
    -0.06
    },{
    -0.06
    تبه
    -0.06
    licos
    -0.06
     Nunes
    -0.06
     daddy
    -0.06
    POSITIVE LOGITS
     사망
    0.07
    (buff
    0.06
    byter
    0.06
     former
    0.06
     ubiquitous
    0.06
    [Byte
    0.06
     spacious
    0.06
    <Student
    0.06
    	INNER
    0.06
    .SpringBootTest
    0.06
    Act Density 0.004%

    No Known Activations