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

    Neuronpedia

    INDEX
    Explanations

    concept of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     scen
    -0.10
    wares
    -0.09
    /by
    -0.09
    dl
    -0.09
    âĢIJâĢIJ
    -0.08
    htt
    -0.08
    éĴ
    -0.08
    bett
    -0.08
    imal
    -0.08
    767
    -0.08
    POSITIVE LOGITS
     itself
    0.13
    ism
    0.11
    iface
    0.10
    ubi
    0.10
     بÙĪدÙĨ
    0.09
    à¹ģละà¸ģาร
    0.09
    877
    0.09
     lod
    0.09
    hood
    0.09
    571
    0.09
    Act Density 0.160%

    No Known Activations