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

    Neuronpedia

    INDEX
    Explanations

    you forget, you can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ן
    0.52
     COUR
    0.50
    EL
    0.49
    IMUM
    0.48
     Oakland
    0.47
    Fach
    0.47
     רו
    0.46
     Надо
    0.46
    Lapangan
    0.46
    ע
    0.46
    POSITIVE LOGITS
     bertujuan
    0.60
    ことも
    0.57
    ੀਆਂ
    0.53
    他の
    0.52
    𝚐
    0.52
     bantuan
    0.52
    𝚎
    0.52
    kyverno
    0.51
    жа
    0.51
     cation
    0.51
    Act Density 0.368%

    No Known Activations