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

    Neuronpedia

    INDEX
    Explanations

    bargain collectively

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bleau
    0.42
    निटी
    0.41
    য়দ
    0.40
     सिंपली
    0.40
    ttemberg
    0.40
    ereum
    0.39
     이에
    0.39
     Vikipedi
    0.39
    朋友圈
    0.38
    াক্রমে
    0.37
    POSITIVE LOGITS
    ST
    0.42
     best
    0.38
    t
    0.38
     oxy
    0.37
    0.37
    evo
    0.37
    野
    0.37
     t
    0.37
     ones
    0.36
    tor
    0.36
    Act Density 0.000%

    No Known Activations