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

    Neuronpedia

    INDEX
    Explanations

    tal followed by specific sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    トラ
    0.38
    ซีน
    0.38
    illerie
    0.38
     stung
    0.37
     Mitsubishi
    0.37
     ಕಡಿ
    0.37
     Provisions
    0.36
     ইঙ্গিত
    0.36
     ঠাকুরের
    0.36
    डिंग
    0.36
    POSITIVE LOGITS
    Tal
    1.09
     Tal
    1.02
     tal
    1.02
     TAL
    0.72
     тала
    0.71
    tal
    0.70
    isman
    0.68
     탈
    0.66
     Talbot
    0.63
    탈
    0.63
    Act Density 0.005%

    No Known Activations