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

    Neuronpedia

    INDEX
    Explanations

    Number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ρχ
    -0.07
     पह
    -0.06
    world
    -0.06
    Energy
    -0.06
    .capacity
    -0.06
    لط
    -0.06
    CONST
    -0.06
     찾아
    -0.06
    .getInputStream
    -0.06
     Barbar
    -0.06
    POSITIVE LOGITS
     vzděl
    0.07
     неболь
    0.07
    andez
    0.06
    ,”
    0.06
    ..."↵↵
    0.06
     chlap
    0.06
     plaisir
    0.06
    ,"
    0.06
    ...\
    0.06
    �
    0.06
    Act Density 0.001%

    No Known Activations