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

    Neuronpedia

    INDEX
    Explanations

    “

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     consistently
    -0.07
     perman
    -0.07
    respons
    -0.07
     casi
    -0.06
    ození
    -0.06
    /logs
    -0.06
     largely
    -0.06
     ب
    -0.06
     vůbec
    -0.06
    _DOWNLOAD
    -0.06
    POSITIVE LOGITS
    thy
    0.06
    hread
    0.06
    Colors
    0.06
    zM
    0.06
    	spin
    0.06
    _principal
    0.06
    reeze
    0.06
    _exit
    0.06
     crc
    0.06
    타
    0.06
    Act Density 0.000%

    No Known Activations