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

    Neuronpedia

    INDEX
    Explanations

    drawer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     всіх
    -0.07
    atives
    -0.07
    likelihood
    -0.07
    antd
    -0.07
    ikk
    -0.07
     save
    -0.07
    ,Y
    -0.07
    _bulk
    -0.06
     inhibitor
    -0.06
     Epic
    -0.06
    POSITIVE LOGITS
    .plus
    0.07
    __":↵
    0.06
    .charAt
    0.06
     sidel
    0.06
     Pul
    0.06
     sailor
    0.06
    ationship
    0.06
    /rem
    0.06
     Cous
    0.06
    _aug
    0.05
    Act Density 0.006%

    No Known Activations