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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wizards
    -0.07
     
    -0.07
     Moodle
    -0.06
    .RES
    -0.06
    €�
    -0.06
     amino
    -0.06
     adres
    -0.06
     Premiership
    -0.06
     elsewhere
    -0.06
     startPosition
    -0.06
    POSITIVE LOGITS
    ($__
    0.06
    溪
    0.06
     вор
    0.06
    кових
    0.06
    apro
    0.06
     πρό
    0.06
    ้องน
    0.06
    askell
    0.06
     nákup
    0.06
     net
    0.06
    Act Density 0.003%

    No Known Activations