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

    Neuronpedia

    INDEX
    Explanations

    them

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jquery
    -0.07
    lates
    -0.07
    jdk
    -0.06
    führ
    -0.06
    reten
    -0.06
    نج
    -0.06
    ikat
    -0.06
     вули
    -0.06
     iken
    -0.06
    ilihan
    -0.06
    POSITIVE LOGITS
     can
    0.06
    。そして
    0.06
     regrets
    0.06
     Ach
    0.06
     c
    0.06
    ?↵↵↵
    0.06
    巴
    0.06
     dolphin
    0.06
    ,p
    0.06
     red
    0.06
    Act Density 0.000%

    No Known Activations