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

    Neuronpedia

    INDEX
    Explanations

    insert, prince, swap, replace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sm
    0.43
    ppings
    0.42
    TES
    0.40
     право
    0.38
    of
    0.38
    OptionPane
    0.38
    vacc
    0.38
    oppers
    0.37
    quest
    0.37
    datepicker
    0.37
    POSITIVE LOGITS
     prince
    0.41
     forced
    0.40
     inserted
    0.40
     Heard
    0.40
     Insert
    0.39
     insert
    0.39
     Prince
    0.38
    獻
    0.38
     geologic
    0.38
     receptacle
    0.38
    Act Density 0.000%

    No Known Activations