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

    Neuronpedia

    INDEX
    Explanations

    concatenate, split, pop

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ي
    1.84
    يا
    1.60
    ین
    1.51
    ו
    1.48
     aperto
    1.48
    ق
    1.46
    aient
    1.45
    nya
    1.43
    ના
    1.38
    י
    1.38
    POSITIVE LOGITS
     दीजिएगा
    1.44
    crumbs
    1.42
    WITT
    1.41
    🠀
    1.40
    드립니다
    1.31
     therefrom
    1.30
     therewith
    1.30
     निर्वा
    1.28
     kè
    1.28
     Marley
    1.27
    Act Density 0.072%

    No Known Activations