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

    Neuronpedia

    INDEX
    Explanations

    Swedish words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IEC
    0.41
    вані
    0.38
     céré
    0.37
    ྡ
    0.37
    ಕ್ತಿ
    0.37
    athor
    0.37
     vyh
    0.37
    䉿
    0.36
     linie
    0.36
    asamb
    0.35
    POSITIVE LOGITS
     Det
    0.61
    Det
    0.60
     Jag
    0.55
     Men
    0.51
     Vi
    0.50
    Jag
    0.50
    Men
    0.49
     Den
    0.48
    Vi
    0.47
     Tank
    0.47
    Act Density 0.001%

    No Known Activations