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

    Neuronpedia

    INDEX
    Explanations

    Code/Configuration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fourth
    -0.06
    Sk
    -0.06
    _Settings
    -0.06
    (Operation
    -0.06
    Vector
    -0.06
    ++;↵↵
    -0.06
    คอม
    -0.06
    .Stop
    -0.06
     Videos
    -0.06
     чи
    -0.06
    POSITIVE LOGITS
     stran
    0.06
     первой
    0.06
     containment
    0.06
     outward
    0.06
     cryptoc
    0.06
    ління
    0.06
     Veranst
    0.06
     zest
    0.06
     bracket
    0.06
    inness
    0.06
    Act Density 0.062%

    No Known Activations