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

    Neuronpedia

    INDEX
    Explanations

    IPL and SDGs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    。
    0.45
    MD
    0.40
    instruction
    0.39
    stack
    0.39
    nt
    0.37
     instructions
    0.37
    лана
    0.37
     tooling
    0.36
     stack
    0.36
     شغ
    0.36
    POSITIVE LOGITS
    ٰ
    0.46
     Jerusalem
    0.45
     Inhalte
    0.45
     மு
    0.44
     कर्ज
    0.43
     puriso
    0.43
     mengisi
    0.42
     merkezi
    0.42
     prayed
    0.42
    ází
    0.42
    Act Density 0.001%

    No Known Activations