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

    Neuronpedia

    INDEX
    Explanations

    code/formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CursorPosition
    -0.08
    Sock
    -0.07
     StringTokenizer
    -0.07
    іп
    -0.07
     spat
    -0.07
     epidemic
    -0.07
    subs
    -0.07
     stri
    -0.07
     asleep
    -0.07
     prostitutes
    -0.06
    POSITIVE LOGITS
     개발
    0.06
    TODO
    0.06
     nevy
    0.06
     cream
    0.06
    encv
    0.06
    €
    0.06
     Oxygen
    0.06
     deja
    0.05
     '';↵
    0.05
    knife
    0.05
    Act Density 0.019%

    No Known Activations