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

    Neuronpedia

    INDEX
    Explanations

    Size/scaling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    required
    -0.07
    違
    -0.06
    uintptr
    -0.06
    ihanna
    -0.06
     Meh
    -0.06
     Rihanna
    -0.06
     "}";↵
    -0.06
    icine
    -0.06
     IX
    -0.06
    θυ
    -0.06
    POSITIVE LOGITS
     Datensch
    0.07
    Browser
    0.07
    oure
    0.07
     ferry
    0.06
    omething
    0.06
     rendez
    0.06
     tensor
    0.06
    ，则
    0.06
     غير
    0.06
    lesia
    0.06
    Act Density 0.010%

    No Known Activations