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

    Neuronpedia

    INDEX
    Explanations

    Defendant. Actions. Secrets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     angeles
    1.02
    ఎల్
    0.99
     updates
    0.95
    েরিক
    0.91
    \|_{\
    0.90
     update
    0.89
    cape
    0.89
     revisions
    0.88
    رام
    0.88
    TABLE
    0.87
    POSITIVE LOGITS
     automó
    1.10
    úblic
    1.06
     प्रूव
    1.06
    inander
    1.06
    isição
    1.05
    údo
    1.05
    ून
    1.05
     samochod
    1.05
    на
    1.05
    નગર
    1.05
    Act Density 0.000%

    No Known Activations