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

    Neuronpedia

    INDEX
    Explanations

    Editing and publishing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     object
    0.78
     objects
    0.72
     preconditions
    0.70
     autograph
    0.70
     identifying
    0.69
    wired
    0.69
     wrote
    0.68
     weight
    0.67
     describing
    0.67
     opinion
    0.67
    POSITIVE LOGITS
     Editor
    0.98
     Editing
    0.89
     Novels
    0.88
    Editor
    0.87
    𝘧
    0.81
    𝘪
    0.81
    Celestial
    0.80
    newPage
    0.80
    щению
    0.79
    Editors
    0.79
    Act Density 0.000%

    No Known Activations