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

    Neuronpedia

    INDEX
    Explanations

    I followed by past actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     رکھتا
    0.42
     Bukan
    0.40
    <unused2130>
    0.38
     servent
    0.38
     सालों
    0.37
     unites
    0.37
    られます
    0.36
     Gest
    0.36
    とその
    0.35
    ipherals
    0.35
    POSITIVE LOGITS
     enjoyed
    0.86
     spent
    0.75
     ended
    0.75
     accomplished
    0.69
     did
    0.68
     successfully
    0.68
     narrowly
    0.65
    successfully
    0.65
    spent
    0.65
     discovered
    0.64
    Act Density 0.010%

    No Known Activations