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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     стоит
    -0.07
    stri
    -0.07
     单
    -0.06
     mommy
    -0.06
     stripped
    -0.06
    čast
    -0.06
    vič
    -0.06
     să
    -0.06
    526
    -0.06
     Mild
    -0.06
    POSITIVE LOGITS
    {@
    0.06
    وة
    0.06
    ilenames
    0.06
    �
    0.06
    developer
    0.06
     học
    0.06
     благодаря
    0.06
    BuilderFactory
    0.06
     IPPROTO
    0.06
    OURSE
    0.06
    Act Density 0.193%

    No Known Activations