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

    Neuronpedia

    INDEX
    Explanations

    cyberthreat defense

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unsound
    0.38
     hazelnuts
    0.37
     perso
    0.37
     hide
    0.37
     annealed
    0.36
     af
    0.36
     taint
    0.36
     extraneous
    0.35
    strument
    0.35
    ជ្រ
    0.35
    POSITIVE LOGITS
     (§
    0.63
     $(
    0.55
     (£
    0.52
     ($\
    0.49
     $(\
    0.49
     [§
    0.49
     ($
    0.48
     [
    0.47
     (~
    0.47
     (#
    0.46
    Act Density 0.073%

    No Known Activations