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

    Neuronpedia

    INDEX
    Explanations

    setting mode or seed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GoObject
    0.38
    aaS
    0.38
    ely
    0.37
     escorted
    0.37
     wrap
    0.36
    ឈ្មោះ
    0.36
    wrapped
    0.36
     DMBT
    0.36
    ন্ব
    0.36
     wrapped
    0.35
    POSITIVE LOGITS
     Einstellung
    0.43
     Needed
    0.40
     setDefault
    0.40
     preven
    0.39
    Needed
    0.39
    setInt
    0.39
     needed
    0.38
     inhib
    0.38
     preempt
    0.38
     necessary
    0.38
    Act Density 0.082%

    No Known Activations