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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Bridge
    -0.07
     seeming
    -0.07
    ulates
    -0.06
     arrows
    -0.06
    focused
    -0.06
    refresh
    -0.06
    _full
    -0.06
     Arc
    -0.06
    @param
    -0.06
    Alabama
    -0.06
    POSITIVE LOGITS
    대표
    0.07
    ******
↵
    0.07
    "];
    0.06
    贫
    0.06
    圍
    0.06
     govern
    0.06
    enské
    0.06
    設備
    0.06
    trand
    0.06
     пар
    0.06
    Act Density 0.044%

    No Known Activations