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

    Neuronpedia

    INDEX
    Explanations

    Senate, senior, developer, data scientist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     />
    0.88
     Такой
    0.87
    0.84
    ase
    0.83
    esse
    0.80
    iel
    0.80
     কিন্ত
    0.80
    ти
    0.79
    olle
    0.77
    œil
    0.76
    POSITIVE LOGITS
     tantamount
    0.96
    ША
    0.91
    الش
    0.90
    콥
    0.89
    ΙΑ
    0.88
    俩
    0.88
    "',
    0.84
    Shr
    0.84
    LONDON
    0.83
     शुक्ल
    0.82
    Act Density 0.000%

    No Known Activations