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

    Neuronpedia

    INDEX
    Explanations

    predictability and planning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    distribution
    -0.07
    outside
    -0.07
    language
    -0.06
    ientes
    -0.06
    Addon
    -0.06
    영어
    -0.06
     beams
    -0.06
    xyz
    -0.06
     polar
    -0.06
     escaped
    -0.06
    POSITIVE LOGITS
     　　　　　　
    0.06
    TableView
    0.06
    obus
    0.06
     Ronnie
    0.06
    .SpringBootApplication
    0.06
    ювання
    0.06
    怎
    0.06
     Společ
    0.06
     Ř
    0.06
     İs
    0.06
    Act Density 0.151%

    No Known Activations