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

    Neuronpedia

    INDEX
    Explanations

    warning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (R
    -0.07
    쓰
    -0.06
     TMP
    -0.06
     gadget
    -0.06
    Eq
    -0.06
     gadgets
    -0.06
    -Year
    -0.06
    kor
    -0.06
     Portal
    -0.06
     steroid
    -0.06
    POSITIVE LOGITS
     seasoned
    0.08
    journal
    0.07
     Landing
    0.07
     robots
    0.06
     پزش
    0.06
    urre
    0.06
    haft
    0.06
    closure
    0.06
    Heading
    0.06
     int
    0.06
    Act Density 0.003%

    No Known Activations