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

    Neuronpedia

    INDEX
    Explanations

    ROM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     желуд
    -0.07
     Trường
    -0.07
    sız
    -0.06
     �
    -0.06
     Rapids
    -0.06
    žení
    -0.06
     festive
    -0.06
     λι
    -0.06
    adera
    -0.06
    WhatsApp
    -0.06
    POSITIVE LOGITS
     ROM
    0.10
    -ROM
    0.08
     Rom
    0.07
    _PLUGIN
    0.07
    (REG
    0.07
    名
    0.06
     ob
    0.06
    น
    0.06
     thermometer
    0.06
     tom
    0.06
    Act Density 0.001%

    No Known Activations