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

    Neuronpedia

    INDEX
    Explanations

    here and similar locational indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ukkan
    0.63
    らかじめ
    0.61
    annels
    0.61
    それは
    0.57
    ammable
    0.56
    omis
    0.55
    ambra
    0.55
    öld
    0.54
     پوچھا
    0.54
    كله
    0.54
    POSITIVE LOGITS
     here
    6.03
     aquí
    5.03
     здесь
    4.98
     aqui
    4.74
     Here
    4.70
    here
    4.62
     aici
    4.48
    Here
    4.47
     هنا
    4.39
     HERE
    4.35
    Act Density 0.333%

    No Known Activations