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

    Neuronpedia

    INDEX
    Explanations

    by optimizingby preventing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Patients
    0.44
     Viruses
    0.42
    Mouse
    0.42
    Patients
    0.42
     Revolution
    0.40
     Audible
    0.40
    Hearing
    0.40
     Notes
    0.39
     Hearing
    0.39
     Points
    0.39
    POSITIVE LOGITS
     disgruntled
    0.53
     asserted
    0.53
    ലു
    0.51
     behaupt
    0.48
    珍惜
    0.48
    ন্তী
    0.47
     ಮಾಡಿ
    0.47
     annoyed
    0.47
     lasci
    0.47
     saiu
    0.47
    Act Density 0.005%

    No Known Activations