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

    Neuronpedia

    INDEX
    Explanations

    Heading somewhere

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dirty
    -0.07
    iper
    -0.06
     jouer
    -0.06
     hotter
    -0.06
     Purdue
    -0.06
     opera
    -0.06
     Wow
    -0.06
    suppress
    -0.06
    ріп
    -0.06
     Actually
    -0.06
    POSITIVE LOGITS
    Autowired
    0.07
    OLUM
    0.07
    ΑΡ
    0.06
     slew
    0.06
     هزینه
    0.06
     informative
    0.06
    Moving
    0.06
     prostor
    0.06
     Ma
    0.06
    /lab
    0.06
    Act Density 0.112%

    No Known Activations