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

    Neuronpedia

    INDEX
    Explanations

    modelpretrained hardware model numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Osmanlı
    0.27
    飏
    0.27
    糇
    0.26
     NavBar
    0.26
     ocasion
    0.25
    <unused2176>
    0.25
    秽
    0.25
     Risiko
    0.25
    InCategory
    0.25
    胭
    0.25
    POSITIVE LOGITS
    ag
    0.34
    l
    0.33
    v
    0.33
    g
    0.32
    B
    0.32
    G
    0.31
    C
    0.31
    x
    0.31
    1
    0.31
    L
    0.31
    Act Density 0.111%

    No Known Activations