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

    Neuronpedia

    INDEX
    Explanations

    open-weights model widely

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    桶
    0.37
    辺
    0.36
    vera
    0.35
     hop
    0.34
    臺
    0.33
    疵
    0.33
    headings
    0.33
    bordered
    0.32
     سادہ
    0.32
    ula
    0.32
    POSITIVE LOGITS
     Marian
    0.40
    PBS
    0.39
    NAM
    0.36
    CNN
    0.36
     Embassy
    0.35
     PBS
    0.35
     Electrochem
    0.34
    AMP
    0.34
    celer
    0.34
    Dipl
    0.34
    Act Density 0.015%

    No Known Activations