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

    Neuronpedia

    INDEX
    Explanations

    особ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     McGregor
    -0.07
     pension
    -0.07
     hospital
    -0.07
     imperial
    -0.07
    sum
    -0.07
    finger
    -0.07
    Physics
    -0.06
    交通
    -0.06
     incontro
    -0.06
    -air
    -0.06
    POSITIVE LOGITS
    特殊
    0.09
    Ос
    0.08
     filenames
    0.07
    ・━・━
    0.07
     特
    0.06
    �다
    0.06
    /book
    0.06
    .V
    0.06
    "}}↵
    0.06
     Caller
    0.06
    Act Density 0.021%

    No Known Activations