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

    Neuronpedia

    INDEX
    Explanations

    taken

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    delta
    -0.07
    Css
    -0.07
    Ros
    -0.07
    leftrightarrow
    -0.07
     Jord
    -0.07
    WritableDatabase
    -0.07
    Rom
    -0.07
    formData
    -0.07
     Edwards
    -0.07
    ordinate
    -0.07
    POSITIVE LOGITS
     taken
    0.21
     Taken
    0.16
    Taken
    0.14
    taken
    0.14
     mistaken
    0.09
     eaten
    0.08
    ken
    0.08
     chosen
    0.08
    aken
    0.07
     undertaken
    0.07
    Act Density 0.010%

    No Known Activations