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

    Neuronpedia

    INDEX
    Explanations

    times

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enant
    -0.29
    inium
    -0.26
     bows
    -0.26
    该éĻ¢
    -0.26
    /Branch
    -0.25
    ;element
    -0.25
    ainen
    -0.25
    artin
    -0.25
    otton
    -0.24
    lobe
    -0.24
    POSITIVE LOGITS
     confront
    0.28
    igy
    0.27
    tu
    0.27
    åĢ¾
    0.26
     menj
    0.26
    éĹ²
    0.25
    èĥ¶
    0.25
    èĢĮæĿ¥
    0.24
    igit
    0.24
    ÑĨи
    0.24
    Act Density 1.735%

    No Known Activations