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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inge
    -0.08
    PREFIX
    -0.07
     Alle
    -0.07
     reef
    -0.06
     Le
    -0.06
    旦
    -0.06
     Như
    -0.06
     haircut
    -0.06
     Sz
    -0.06
     Tunnel
    -0.06
    POSITIVE LOGITS
     hides
    0.07
    تم
    0.07
     různých
    0.07
     passphrase
    0.07
     decals
    0.06
    /calendar
    0.06
     jsonString
    0.06
    입
    0.06
     notifies
    0.06
    _CONFIGURATION
    0.06
    Act Density 0.035%

    No Known Activations