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

    Neuronpedia

    INDEX
    Explanations

    put option

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     chamar
    0.50
     hipot
    0.49
     buhay
    0.49
     financiar
    0.48
    र्नर
    0.47
     namik
    0.47
     supprimer
    0.47
     casco
    0.47
     suport
    0.47
     accentuate
    0.47
    POSITIVE LOGITS
     Americans
    0.44
    Americans
    0.44
    UMI
    0.44
     Southerners
    0.44
    ov
    0.43
    IDS
    0.43
    eg
    0.42
    ids
    0.42
    av
    0.42
    OP
    0.42
    Act Density 0.004%

    No Known Activations