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

    Neuronpedia

    INDEX
    Explanations

    Negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brid
    -0.07
     Already
    -0.06
     magnetic
    -0.06
     estad
    -0.06
     endured
    -0.06
     ballots
    -0.06
    .Thread
    -0.06
    Trip
    -0.06
     Noticed
    -0.06
     Frames
    -0.06
    POSITIVE LOGITS
    avg
    0.06
     że
    0.06
    July
    0.06
    abc
    0.06
    utron
    0.06
     раза
    0.06
     pictureBox
    0.06
     yyyy
    0.06
    iffe
    0.06
    üc
    0.06
    Act Density 0.039%

    No Known Activations