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

    Neuronpedia

    INDEX
    Explanations

    Backing up vehicles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     implies
    -0.07
     созда
    -0.07
    .mo
    -0.07
     flexGrow
    -0.07
     dv
    -0.07
    .mas
    -0.06
     psychologists
    -0.06
    aro
    -0.06
    Tr
    -0.06
     delete
    -0.06
    POSITIVE LOGITS
    θεν
    0.07
     دریا
    0.06
     ail
    0.06
     revolt
    0.06
     genie
    0.06
     attainment
    0.06
    ですね
    0.06
     कव
    0.06
     männ
    0.06
     такой
    0.06
    Act Density 0.033%

    No Known Activations