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

    Neuronpedia

    INDEX
    Explanations

    Road

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LOUD
    -0.07
     corros
    -0.06
    \Validation
    -0.06
    UREMENT
    -0.06
    óg
    -0.06
     команди
    -0.06
    Щ
    -0.06
    _CHILD
    -0.06
     mel
    -0.06
     Degrees
    -0.06
    POSITIVE LOGITS
     fe
    0.06
    อย
    0.06
     الحديث
    0.06
    вание
    0.06
     expressing
    0.06
    ụp
    0.06
     identifies
    0.06
     consult
    0.06
     frequently
    0.06
    	host
    0.06
    Act Density 0.017%

    No Known Activations